© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4861
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to people's names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token <|endoftext|>

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.82
    ¬¼
    -0.77
    ĨĴ
    -0.75
    essee
    -0.65
    eries
    -0.63
     fold
    -0.62
    eners
    -0.62
    stakes
    -0.60
    oway
    -0.60
    isSpecialOrderable
    -0.59
    POSITIVE LOGITS
    rival
    1.22
    ansas
    1.17
    ranged
    1.15
    ithmetic
    1.14
    duino
    1.11
    thritis
    1.08
    ranging
    1.08
    lington
    1.07
    gent
    1.07
    lene
    1.07
    Activations Density 0.021%

    No Known Activations