© 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. 7-RES-JB
    11. 167
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to countries, organizations, and groups involved in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hai
    -0.78
    prem
    -0.78
    ounded
    -0.72
     Supplemental
    -0.67
    utenberg
    -0.65
    ilon
    -0.65
    netflix
    -0.65
    ounding
    -0.65
    abre
    -0.64
    pi
    -0.64
    POSITIVE LOGITS
     whatsoever
    1.40
     imaginable
    1.40
     except
    1.12
     conceivable
    1.02
     anywhere
    0.93
     besides
    0.88
    soever
    0.87
     irrespective
    0.84
     describ
    0.84
     else
    0.83
    Activations Density 0.215%

    No Known Activations