Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18219
    Prev
    Next
    INDEX
    Explanations

    timestamps in the format of hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and date information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥİ
    -0.70
    gently
    -0.67
    ©¶æ
    -0.64
     doub
    -0.61
     Kirin
    -0.59
     mould
    -0.56
     analys
    -0.55
     endors
    -0.53
     differentiated
    -0.53
     Norn
    -0.53
    POSITIVE LOGITS
     IST
    1.09
     PDT
    0.79
     Views
    0.78
     EDT
    0.75
     GMT
    0.74
     PST
    0.72
     Nanto
    0.71
     UTC
    0.71
    pm
    0.68
    Thu
    0.65
    Activations Density 0.067%

    No Known Activations