© 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. 7464
    Prev
    Next
    INDEX
    Explanations

    phrases related to account creation or login instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user account management and authentication

    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
     accompany
    -0.64
    emic
    -0.63
     crib
    -0.62
     tract
    -0.62
     scalp
    -0.61
     ult
    -0.59
     torn
    -0.58
     directions
    -0.57
    hur
    -0.57
     packaged
    -0.56
    POSITIVE LOGITS
    76561
    0.92
     Username
    0.91
     Password
    0.84
     Login
    0.83
    settings
    0.81
    password
    0.77
    oa
    0.75
    Afee
    0.71
     Registration
    0.71
    CHAT
    0.71
    Activations Density 0.063%

    No Known Activations