© 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. 6-RES-JB
    11. 18466
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    references to brackets or citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elys
    -0.81
     nodd
    -0.77
     therap
    -0.74
     redu
    -0.72
     seiz
    -0.71
     sacrific
    -0.69
     snipp
    -0.68
    edIn
    -0.67
     comprom
    -0.66
     handlers
    -0.65
    POSITIVE LOGITS
    sic
    1.60
    ?]
    1.43
    !]
    1.29
    REDACTED
    1.29
    emphasis
    1.18
    insert
    1.17
    Pg
    1.16
    :]
    1.14
    email
    1.12
    âĢ¦]
    1.12
    Activations Density 0.035%

    No Known Activations