© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 24171
    Prev
    Next
    INDEX
    Explanations

    paths and directions expressed in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    sequences of conjunctions and prepositions indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Adapt
    -0.66
    dozen
    -0.64
     Respons
    -0.63
    Effective
    -0.63
    kes
    -0.62
    icult
    -0.62
    eal
    -0.62
    zman
    -0.60
    UF
    -0.59
    unique
    -0.59
    POSITIVE LOGITS
     into
    1.78
     onto
    1.78
     INTO
    1.53
    into
    1.40
     Into
    1.39
     toward
    1.28
     onward
    1.27
     thence
    1.25
     onwards
    1.22
     towards
    1.19
    Activations Density 0.249%

    No Known Activations