© 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. 796
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to departures or changes in positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to departures and changes in leadership or organizational roles

    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
    NI
    -0.63
    ontent
    -0.62
    ocrates
    -0.62
    Ĭ±
    -0.61
    Pros
    -0.61
    EGIN
    -0.59
     Excellence
    -0.58
    ochet
    -0.58
     ILCS
    -0.56
    amina
    -0.56
    POSITIVE LOGITS
     underscores
    1.30
     signifies
    1.18
     raises
    1.16
     reinforces
    1.15
     sends
    1.13
     coincides
    1.12
     brings
    1.11
     undermines
    1.11
     represents
    1.11
     coincided
    1.09
    Activations Density 0.220%

    No Known Activations