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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21228
    Prev
    Next
    INDEX
    Explanations

    the word "No" followed by a high activation value suggesting a negative sentiment or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "No" indicating negative assertions or dismissals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iership
    -0.79
    RAFT
    -0.69
    rn
    -0.68
    rog
    -0.67
    ript
    -0.66
    leaning
    -0.66
    ALE
    -0.64
    ijuana
    -0.62
    ËĪ
    -0.61
    tnc
    -0.60
    POSITIVE LOGITS
     kidding
    1.12
    etheless
    1.08
     matter
    1.03
     wonder
    0.97
     doubt
    0.97
     longer
    0.96
    xious
    0.90
    zzle
    0.83
     sooner
    0.83
    except
    0.82
    Activations Density 0.077%

    No Known Activations