© 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. 10-RES-JB
    11. 13983
    Prev
    Next
    INDEX
    Explanations

    user profiles or forum posts containing a unique identifier or tag

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical identifiers, such as post counts and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nort
    -0.71
     Advocate
    -0.65
     Samar
    -0.60
     earliest
    -0.60
     cradle
    -0.59
     disbelief
    -0.59
     Rash
    -0.58
     phys
    -0.58
     Gina
    -0.57
     Wander
    -0.57
    POSITIVE LOGITS
    ################################
    1.03
    ################
    0.99
    ########
    0.93
    define
    0.90
    ###
    0.85
    MENTS
    0.83
    9
    0.77
    endif
    0.75
    Reply
    0.75
    ł
    0.73
    Activations Density 0.016%

    No Known Activations