© 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. 23364
    Prev
    Next
    INDEX
    Explanations

    phrases related to commissions or commissioned work

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "commissioned" and variations related to commissioning

    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
    corn
    -0.75
    amac
    -0.73
    acca
    -0.72
     Klu
    -0.70
    oland
    -0.69
     Alz
    -0.67
    oya
    -0.67
    Tang
    -0.66
    ophon
    -0.64
    amy
    -0.64
    POSITIVE LOGITS
     commissions
    0.94
     commissioned
    0.91
     commission
    0.81
    isition
    0.77
     artwork
    0.75
     solicitation
    0.73
    smanship
    0.71
     graded
    0.69
    interstitial
    0.69
    eer
    0.68
    Activations Density 0.047%

    No Known Activations