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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 14524
    Prev
    Next
    INDEX
    Explanations

    prices or costs mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    pricing information related to products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igators
    -0.77
    eworks
    -0.75
    igating
    -0.74
     ingred
    -0.72
     tragedies
    -0.72
    liners
    -0.69
    antha
    -0.68
    wings
    -0.66
    ngth
    -0.65
    irlf
    -0.64
    POSITIVE LOGITS
    999
    1.26
    CRIP
    0.92
    CRIPTION
    0.91
    aire
    0.88
    762
    0.86
    å§«
    0.86
    ZI
    0.86
    595
    0.85
    ×Ļ×
    0.85
    ZA
    0.85
    Activations Density 0.017%

    No Known Activations