© 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. 3-RES-JB
    11. 15062
    Prev
    Next
    INDEX
    Explanations

    words related to negative impact or worsening of a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to worsening or exacerbating situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahoo
    -0.84
    atography
    -0.78
    leans
    -0.74
    lean
    -0.72
    earchers
    -0.72
    ather
    -0.70
    bors
    -0.69
    print
    -0.69
    otted
    -0.69
    pta
    -0.68
    POSITIVE LOGITS
     exacerb
    1.14
     aggrav
    0.93
     worsen
    0.88
     exacerbate
    0.84
     infl
    0.78
     exacerbated
    0.76
     havoc
    0.76
     worsened
    0.75
     intensify
    0.74
    ãĥ¼ãĥĨ
    0.73
    Activations Density 0.016%

    No Known Activations