© 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. 10-RES-JB
    11. 21418
    Prev
    Next
    INDEX
    Explanations

    values or quantities inside parentheses or brackets

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and brackets used in various contexts

    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
     buoy
    -0.88
     brim
    -0.81
     cog
    -0.80
     dense
    -0.76
     prone
    -0.76
     embr
    -0.74
     sacrific
    -0.74
     laced
    -0.74
     stern
    -0.74
     flex
    -0.74
    POSITIVE LOGITS
    sic
    1.99
    laughs
    1.55
    insert
    1.41
    former
    1.39
    their
    1.37
    the
    1.37
    emphasis
    1.34
    his
    1.34
    director
    1.31
    ex
    1.30
    Activations Density 0.065%

    No Known Activations