© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11768
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "If" followed by a conditional statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or clauses related to hypothetical situations

    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
    ©¶æ¥µ
    -0.92
    Els
    -0.67
    imar
    -0.66
    NetMessage
    -0.66
    çīĪ
    -0.64
    udeb
    -0.64
    ".[
    -0.63
    ãĥī
    -0.61
    ãĤ¼
    -0.61
     tremend
    -0.60
    POSITIVE LOGITS
     &&
    0.74
     somewhere
    0.72
     somebody
    0.71
     slightest
    0.70
     or
    0.70
    essor
    0.68
     OR
    0.66
     yourself
    0.65
     anymore
    0.65
     please
    0.61
    Activations Density 1.020%

    No Known Activations