© 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. 4-RES-JB
    11. 10177
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to phone numbers

    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
    Materials
    -0.79
    rador
    -0.77
     Shroud
    -0.67
    utenberg
    -0.66
    romy
    -0.65
     rift
    -0.65
    ipation
    -0.65
    struction
    -0.64
    INTON
    -0.63
    quished
    -0.63
    POSITIVE LOGITS
    plates
    1.03
    codes
    0.84
     phones
    0.78
     codes
    0.77
     999
    0.76
     NUM
    0.76
    enance
    0.74
    plate
    0.71
    number
    0.71
    metry
    0.71
    Activations Density 0.031%

    No Known Activations