© 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. 11-RES-JB
    11. 17443
    Prev
    Next
    INDEX
    Explanations

    descriptions of suffering or negative experiences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to suffering or adverse experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enta
    -0.77
    ouf
    -0.72
    hens
    -0.70
    raft
    -0.69
    TRY
    -0.68
    essee
    -0.67
    onomy
    -0.66
    ession
    -0.65
    clusive
    -0.65
    ahoo
    -0.64
    POSITIVE LOGITS
     fools
    1.09
     setbacks
    1.08
     losses
    1.06
     horrend
    0.98
     from
    0.96
     debilitating
    0.92
     terribly
    0.92
     greatly
    0.91
     immensely
    0.89
     horribly
    0.89
    Activations Density 0.082%

    No Known Activations