© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    words related to beverages such as "beer" and references to "Bru" which could refer to a brand or person

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms related to individuals, particularly "Bru" and "Dru."

    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
     Poverty
    -0.75
    urities
    -0.69
    omsky
    -0.64
     lang
    -0.63
    raltar
    -0.62
    Hunt
    -0.60
    rane
    -0.59
     stuffing
    -0.59
     Tud
    -0.59
    gamer
    -0.58
    POSITIVE LOGITS
    ella
    0.86
    aign
    0.79
    uto
    0.76
    inal
    0.76
    inois
    0.76
    iser
    0.75
     Bru
    0.71
    ific
    0.71
     Haram
    0.71
    idan
    0.71
    Activations Density 0.072%

    No Known Activations