© 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. 1-RES-JB
    11. 7585
    Prev
    Next
    INDEX
    Explanations

    the surname "Katz" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names, particularly family names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.82
    ¥ŀ
    -0.80
     contrace
    -0.76
     srf
    -0.72
     circ
    -0.67
     groom
    -0.67
    --------------------------------------------------------
    -0.67
     nurt
    -0.67
     insepar
    -0.67
     incarcer
    -0.67
    POSITIVE LOGITS
    atz
    1.35
    nik
    0.96
    hof
    0.96
    atos
    0.95
    gerald
    0.92
    arella
    0.89
    inian
    0.88
    imus
    0.86
    idy
    0.86
    tz
    0.85
    Activations Density 0.003%

    No Known Activations