© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 1504
    Prev
    Next
    INDEX
    Explanations

    situations or actions involving unexpected or sudden events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the lack of consent or authorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    helle
    -0.72
     Christy
    -0.65
    oret
    -0.65
    nai
    -0.65
    agra
    -0.64
     LL
    -0.60
    olic
    -0.59
    roller
    -0.59
     Klux
    -0.59
    oir
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.27
     interruption
    0.77
     nor
    0.76
     anymore
    0.73
     provocation
    0.72
    dding
    0.71
    fulness
    0.68
    pection
    0.65
     deductions
    0.65
     bloodshed
    0.64
    Activations Density 0.091%

    No Known Activations