© 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. 11-RES-JB
    11. 9903
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or subjects emphasized as significant or unique within the context

    oai_token-act-pair · gpt-3.5-turbo

    references to a singular, significant entity or concept within a context

    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
    osponsors
    -0.74
    ypes
    -0.66
    respective
    -0.65
    raits
    -0.63
    Discover
    -0.63
    ominium
    -0.61
    hops
    -0.61
    illon
    -0.60
    onis
    -0.60
    avascript
    -0.59
    POSITIVE LOGITS
     thing
    0.99
     exception
    0.90
     hundred
    0.87
     eyed
    0.86
     thousand
    0.76
     Hundred
    0.76
     closest
    0.75
     nearest
    0.73
     guy
    0.73
     sided
    0.73
    Activations Density 0.064%

    No Known Activations