© 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. 8-RES-JB
    11. 15182
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or political needs and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the necessity for action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anka
    -0.63
     quir
    -0.58
     Rost
    -0.58
    ihu
    -0.58
    rimination
    -0.56
    empt
    -0.56
    fall
    -0.55
    washer
    -0.55
     Sod
    -0.55
    azar
    -0.55
    POSITIVE LOGITS
    lessly
    1.15
    n
    0.88
     patience
    0.84
     urgently
    0.84
     assurances
    0.82
     attention
    0.77
     reminding
    0.75
     answers
    0.72
    FINE
    0.72
    ONEY
    0.71
    Activations Density 0.077%

    No Known Activations