© 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. 0-RES-JB
    11. 1202
    Prev
    Next
    INDEX
    Explanations

    keywords related to document formatting and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to types or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canal
    -0.67
     kale
    -0.66
     instrumental
    -0.64
     wildfire
    -0.61
     credits
    -0.60
     Cris
    -0.60
     accord
    -0.59
     petition
    -0.58
     Bord
    -0.58
     tape
    -0.58
    POSITIVE LOGITS
    Type
    3.37
    Types
    1.80
    Typ
    1.42
    TYPE
    1.37
    type
    1.34
    Kind
    1.31
    Range
    1.30
    types
    1.27
    Grade
    1.17
    Specific
    1.16
    Activations Density 0.021%

    No Known Activations