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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 5896
    Prev
    Next
    INDEX
    Explanations

    specific page numbers or references within texts

    oai_token-act-pair · gpt-3.5-turbo

    references to bibliographic information or page numbers

    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
    Ô
    -0.66
     Weather
    -0.65
    OWN
    -0.64
     directional
    -0.62
    SHARE
    -0.62
    yles
    -0.61
     Woods
    -0.61
     Shuttle
    -0.61
    uay
    -0.61
    edom
    -0.60
    POSITIVE LOGITS
     âĨij
    0.96
     ff
    0.89
    ]).
    0.86
     quoting
    0.83
    0002
    0.82
     seq
    0.79
    69
    0.77
    455
    0.76
    663
    0.76
     reprinted
    0.76
    Activations Density 0.083%

    No Known Activations