© 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. 9-RES-JB
    11. 18654
    Prev
    Next
    INDEX
    Explanations

    references to physical entry points or ways to access a location

    oai_token-act-pair · gpt-3.5-turbo

    references to entrances and access points in various contexts

    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
    rior
    -0.88
    Series
    -0.76
    VALUE
    -0.71
    enegger
    -0.70
    amera
    -0.68
    cons
    -0.67
    irit
    -0.66
    ulz
    -0.65
    riter
    -0.65
    lance
    -0.64
    POSITIVE LOGITS
    prise
    0.89
    tainment
    0.83
     thereto
    0.82
     gates
    0.81
     INTO
    0.80
    ococ
    0.80
    ibility
    0.78
    ORY
    0.78
    ories
    0.78
    ablishment
    0.75
    Activations Density 0.107%

    No Known Activations