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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 16838
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    oai_token-act-pair · gpt-3.5-turbo

    HTML attributes and values

    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
     BP
    -0.77
     equivalents
    -0.75
     Guth
    -0.69
     Faw
    -0.68
     hoard
    -0.67
    ĵĺ
    -0.67
     endings
    -0.66
     Lis
    -0.66
     bilingual
    -0.65
     bonding
    -0.65
    POSITIVE LOGITS
    http
    1.24
    https
    1.19
    true
    1.13
    false
    1.10
    null
    1.09
    <?
    1.05
    "><
    1.01
    post
    0.99
    external
    0.98
    urn
    0.96
    Activations Density 0.015%

    No Known Activations