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. 7-RES-JB
    6. 16797
    Prev
    Next
    INDEX
    Explanations

    prices or costs mentioned in the text, particularly those that are low or affordable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pricing and cost efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isters
    -0.77
     Debor
    -0.76
    ister
    -0.74
     Ging
    -0.72
     Patriarch
    -0.71
    algia
    -0.65
    ullah
    -0.65
     Boris
    -0.62
     Brun
    -0.60
    atcher
    -0.59
    POSITIVE LOGITS
     expense
    0.84
     apiece
    0.77
     disadvantage
    0.76
     level
    0.74
     disposal
    0.74
     pace
    0.73
     scale
    0.73
     footing
    0.73
     snail
    0.71
     intervals
    0.71
    Activations Density 0.140%

    No Known Activations