© 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. 8-RES-JB
    11. 7573
    Prev
    Next
    INDEX
    Explanations

    mentions of specific websites or organizations with email addresses

    oai_token-act-pair · gpt-3.5-turbo

    the letter "t" appearing frequently in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.71
     exha
    -0.69
     Hitman
    -0.68
     grooming
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    Ĥª
    -0.67
     hemor
    -0.66
    ħĭ
    -0.65
     lax
    -0.65
     behavi
    -0.64
    POSITIVE LOGITS
    ribute
    1.33
    itles
    1.30
    oward
    1.29
    ournament
    1.28
    ribune
    1.28
    urtle
    1.27
    ruly
    1.26
    ween
    1.25
    ribut
    1.25
    ractor
    1.24
    Activations Density 0.049%

    No Known Activations