© 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. 7-RES-JB
    11. 23457
    Prev
    Next
    INDEX
    Explanations

    references to various entities, actions, or concepts that encompass a wide scope or all-encompassing extent

    oai_token-act-pair · gpt-3.5-turbo

    references to universality or generality across multiple contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annon
    -0.67
    rers
    -0.65
    rer
    -0.63
    tle
    -0.61
    ahime
    -0.61
    only
    -0.58
    oother
    -0.57
     anesthesia
    -0.56
    reements
    -0.55
    abre
    -0.55
    POSITIVE LOGITS
     imaginable
    1.34
    soever
    1.10
    pires
    1.02
     except
    0.93
     conceivable
    0.91
     whatsoever
    0.90
    except
    0.90
     EVER
    0.86
     mosqu
    0.81
     hereafter
    0.75
    Activations Density 0.512%

    No Known Activations