© 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. 9186
    Prev
    Next
    INDEX
    Explanations

    phrases expressing caution or warning

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or expressions indicating futility or impossibility

    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
    CI
    -0.87
    Streamer
    -0.67
    KNOWN
    -0.66
     Cosponsors
    -0.65
    estern
    -0.64
    ahime
    -0.61
    Tracker
    -0.61
    ciating
    -0.61
    NRS
    -0.61
     OCT
    -0.60
    POSITIVE LOGITS
     suffice
    1.20
     dissu
    1.20
     solve
    1.13
     affect
    1.12
     deter
    1.10
     satisfy
    1.07
     happen
    1.06
     matter
    1.06
     necessarily
    1.04
     detract
    1.03
    Activations Density 0.115%

    No Known Activations