© 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. 11-RES-JB
    11. 7088
    Prev
    Next
    INDEX
    Explanations

    phrases related to being above a certain level or standard

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deal
    -0.69
    NV
    -0.68
    ãĤ¹ãĥĪ
    -0.65
    OVER
    -0.63
    ument
    -0.63
    Creat
    -0.61
    DAY
    -0.61
    NetMessage
    -0.61
    alloc
    -0.59
    cycles
    -0.59
    POSITIVE LOGITS
    ground
    1.49
    mentioned
    1.18
     ground
    1.13
     average
    0.96
    average
    0.90
     sea
    0.86
     freezing
    0.83
     Ground
    0.83
     Average
    0.82
     decks
    0.79
    Activations Density 0.054%

    No Known Activations