© 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. 17551
    Prev
    Next
    INDEX
    Explanations

    strong and impactful words or phrases, particularly ones related to intense change or emotion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dramatic" and its variations

    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
    ©¶æ
    -0.83
    mun
    -0.69
    ossier
    -0.68
    igun
    -0.68
    rahim
    -0.68
    unte
    -0.67
    porter
    -0.67
    cellent
    -0.67
    iband
    -0.67
    Ĥ¬
    -0.67
    POSITIVE LOGITS
     leaps
    0.87
    istically
    0.85
    istic
    0.82
     events
    0.80
     feats
    0.78
    aneously
    0.77
     amounts
    0.77
     transformations
    0.76
     departure
    0.76
    200000
    0.76
    Activations Density 0.031%

    No Known Activations