© 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. 6-RES-JB
    11. 14447
    Prev
    Next
    INDEX
    Explanations

    sentence endings or specific symbols that signal the end of a text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional or sensory experiences

    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
    xual
    -0.84
     scrap
    -0.79
    onte
    -0.79
     Blackwell
    -0.73
     gard
    -0.71
     allied
    -0.69
     friendly
    -0.67
     interested
    -0.67
    hes
    -0.66
    ional
    -0.65
    POSITIVE LOGITS
    Reason
    1.01
    Section
    1.01
    ?????-?????-
    0.99
    Unless
    0.96
    Added
    0.93
    Writing
    0.93
    Comment
    0.91
    Most
    0.90
    Since
    0.88
    advertising
    0.88
    Activations Density 0.214%

    No Known Activations