© 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. 19743
    Prev
    Next
    INDEX
    Explanations

    contractions of "can not" (canâĢˆĻt) followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can't"

    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
    CVE
    -0.81
     SetTextColor
    -0.64
     Gleaming
    -0.61
     continents
    -0.58
     Houses
    -0.57
     scen
    -0.56
     tremend
    -0.56
     rall
    -0.55
    soType
    -0.55
     behavi
    -0.55
    POSITIVE LOGITS
    urtle
    1.02
    weet
    0.96
    otally
    0.84
    urtles
    0.83
    ubs
    0.82
    omp
    0.82
    olkien
    0.81
    ween
    0.80
    ruly
    0.79
    ribe
    0.79
    Activations Density 0.027%

    No Known Activations