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. 4-RES-JB
    6. 23612
    Prev
    Next
    INDEX
    Explanations

    personal names, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the surname Gardner or Garland

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

    No Comments

    Negative Logits
    olitan
    -0.89
    okes
    -0.87
    oke
    -0.86
    avez
    -0.84
    oct
    -0.79
    odan
    -0.79
    olving
    -0.74
    alm
    -0.74
    azeera
    -0.74
    esthes
    -0.73
    POSITIVE LOGITS
     Gardner
    0.82
    llan
    0.77
     Mechdragon
    0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.71
    rier
    0.71
    vernment
    0.69
    bread
    0.68
     Optimus
    0.67
    glass
    0.65
     Gree
    0.65
    Activations Density 0.017%

    No Known Activations