© 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. 6-RES-JB
    11. 21828
    Prev
    Next
    INDEX
    Explanations

    phrases prompting the reader to check out something or directing them to further content

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging readers to engage with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOD
    -0.76
    NetMessage
    -0.74
    ulton
    -0.71
    cffffcc
    -0.71
    ãĥĨãĤ£
    -0.69
    EStreamFrame
    -0.69
    SAY
    -0.66
    CONCLUS
    -0.66
    minist
    -0.64
    Untitled
    -0.64
    POSITIVE LOGITS
    ers
    1.06
    etts
    1.00
    mate
    0.94
    points
    0.93
    lists
    0.90
    er
    0.89
    hee
    0.88
    list
    0.86
    boxes
    0.80
    ups
    0.79
    Activations Density 0.016%

    No Known Activations