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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11708
    Prev
    Next
    INDEX
    Explanations

    sentences with strong emotional judgments

    oai_token-act-pair · gpt-3.5-turbo

    dismissive or negative statements about beliefs or statements perceived as nonsensical

    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
    esses
    -0.93
    esse
    -0.91
    staking
    -0.88
     clustered
    -0.81
    estones
    -0.79
     conduc
    -0.75
     toget
    -0.75
    enaries
    -0.75
    emaker
    -0.75
    usalem
    -0.75
    POSITIVE LOGITS
     Worse
    1.24
     Shame
    1.03
     Especially
    1.02
     Saying
    0.97
     Why
    0.96
     Instead
    0.96
     Firstly
    0.95
     Rape
    0.92
     Stupid
    0.90
     Statements
    0.89
    Activations Density 0.551%

    No Known Activations