© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    phrases describing significant changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "changed" in various contexts

    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
    mination
    -0.70
    alty
    -0.68
    stra
    -0.67
    hold
    -0.67
    Vs
    -0.64
    beit
    -0.63
    ictionary
    -0.62
    verse
    -0.61
    ç«
    -0.61
    otropic
    -0.61
    POSITIVE LOGITS
     dramatically
    0.88
     drastically
    0.83
    ĸļ
    0.83
    amorph
    0.80
     psychiat
    0.74
    elvet
    0.72
    ilver
    0.70
     perceptions
    0.69
     Consent
    0.69
     abruptly
    0.69
    Activations Density 0.047%

    No Known Activations