© 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. 10-RES-JB
    11. 17291
    Prev
    Next
    INDEX
    Explanations

    expressions related to signing up

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletter subscriptions and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olina
    -0.68
    ¶ħ
    -0.65
    soever
    -0.62
    gypt
    -0.57
     Deaths
    -0.57
     bragging
    -0.57
    Ĭ±
    -0.57
     finer
    -0.56
    ignore
    -0.55
     successors
    -0.54
    POSITIVE LOGITS
    */(
    0.69
    iked
    0.66
    âĹ¼
    0.63
    ãĥŁ
    0.62
    roud
    0.60
    ÃĹ
    0.59
    agascar
    0.59
    yles
    0.59
    ete
    0.58
     Takeru
    0.57
    Activations Density 0.017%

    No Known Activations