© 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. 16762
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving credibility or support

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "some."

    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
    raid
    -0.85
    ocene
    -0.79
    rupted
    -0.76
    yrinth
    -0.70
    gon
    -0.69
    SPONSORED
    -0.69
    ean
    -0.65
    ip
    -0.64
    olester
    -0.63
    ampire
    -0.63
    POSITIVE LOGITS
    place
    1.27
     semblance
    1.23
    body
    1.04
    ones
    0.97
     sort
    0.94
     meaningful
    0.88
     decent
    0.87
     additional
    0.83
     tangible
    0.82
     extra
    0.81
    Activations Density 0.079%

    No Known Activations