Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9787
    Prev
    Next
    INDEX
    Explanations

    organizations and groups mentioned in a political or advocacy context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -0.87
     simulator
    -0.77
     intercept
    -0.75
     setup
    -0.75
     screens
    -0.71
    gery
    -0.71
     dishes
    -0.70
     waters
    -0.69
     lapse
    -0.69
    setup
    -0.69
    POSITIVE LOGITS
     NAACP
    1.31
     advocacy
    1.31
     ACLU
    1.19
     Friends
    1.15
     Coalition
    1.13
     Association
    1.11
     Advoc
    1.10
     Concern
    1.06
     nonprofit
    1.06
     Parents
    1.05
    Activations Density 0.565%

    No Known Activations