© 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. 7-RES-JB
    11. 17197
    Prev
    Next
    INDEX
    Explanations

    terms related to computer coding or formatting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "âĢ", which might indicate specific formatting or encoding issues in the document

    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
    WARD
    -0.67
     Lob
    -0.65
     Naz
    -0.64
     Marble
    -0.63
    ographer
    -0.62
     Bohem
    -0.62
     snail
    -0.61
     Whit
    -0.60
     juggling
    -0.60
     Opera
    -0.59
    POSITIVE LOGITS
    selves
    1.07
    hip
    0.96
    chool
    0.96
    everal
    0.90
    iege
    0.87
    overe
    0.85
    itute
    0.80
    ¹
    0.79
    agree
    0.79
    Ĵ
    0.79
    Activations Density 0.204%

    No Known Activations