© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4097
    Prev
    Next
    INDEX
    Explanations

    phrases related to objections or refusals concerning various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.13
    0.6%
    156
    +0.10
    0.5%
    561
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.13
    0.02
    68
    +0.10
    0.02
    750
    +0.10
    0.01
    Negative Logits
    Helper
    -0.81
    rette
    -0.73
     RPM
    -0.68
     Loaded
    -0.67
     NT
    -0.67
     GS
    -0.66
     OT
    -0.66
     Recovery
    -0.66
    sand
    -0.65
    NAS
    -0.64
    POSITIVE LOGITS
     bothering
    0.89
     objections
    0.85
     inconven
    0.79
     bother
    0.79
     detract
    0.79
     interfering
    0.74
     hesitate
    0.73
     disagree
    0.71
    matter
    0.71
    blance
    0.69
    Activations Density 0.191%

    No Known Activations