© 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. 7-RES-JB
    11. 13439
    Prev
    Next
    INDEX
    Explanations

    numerical and special characters within syntax, possibly related to programming language code

    oai_token-act-pair · gpt-3.5-turbo

    strings that include patterns of alphanumeric characters or special symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manif
    -0.83
     mathemat
    -0.70
     Chambers
    -0.69
     conduc
    -0.67
     nodd
    -0.67
     confir
    -0.66
     experien
    -0.65
     fortun
    -0.65
     practiced
    -0.65
     compulsion
    -0.64
    POSITIVE LOGITS
    gt
    1.02
    amp
    0.93
    display
    0.93
    album
    0.92
    ohm
    0.88
    &
    0.84
    ioch
    0.83
    ;;;;;;;;;;;;
    0.83
    define
    0.82
    </
    0.82
    Activations Density 0.019%

    No Known Activations