© 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. 11-RES-JB
    11. 9868
    Prev
    Next
    INDEX
    Explanations

    requests to verify that the user is not a robot

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a verification or authentication process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinnikuman
    -0.62
     conduc
    -0.61
    }}}
    -0.55
     confir
    -0.53
    glers
    -0.53
     Gathering
    -0.52
     distingu
    -0.52
    GES
    -0.50
    é¾įå¥ij士
    -0.49
     Colleges
    -0.49
    POSITIVE LOGITS
    erc
    0.63
    user
    0.60
     spam
    0.58
    essage
    0.57
    registered
    0.57
     dummy
    0.56
    roid
    0.55
    redd
    0.55
     robot
    0.54
     PsyNet
    0.54
    Activations Density 0.019%

    No Known Activations