© 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. 6818
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or recurrent events

    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
    \\\\\\\\
    -0.62
     :(
    -0.57
     Mub
    -0.57
    .�
    -0.56
    .")
    -0.55
     looph
    -0.55
     Adin
    -0.54
     [];
    -0.54
    Ö¼
    -0.54
    eve
    -0.54
    POSITIVE LOGITS
     respectively
    0.87
     etc
    0.82
    ?,
    0.80
    etheless
    0.69
     remains
    0.67
    odan
    0.66
     becomes
    0.65
    ?),
    0.64
     seems
    0.63
    thing
    0.60
    Activations Density 0.934%

    No Known Activations