© 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. 14900
    Prev
    Next
    INDEX
    Explanations

    issues related to subscription, specifically error messages related to email subscription attempts

    oai_token-act-pair · gpt-3.5-turbo

    negative constructs and denial

    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
    bush
    -0.86
    facts
    -0.71
    WAY
    -0.70
    bats
    -0.69
    itiz
    -0.65
    Way
    -0.63
    cases
    -0.62
     Mant
    -0.62
     Grimoire
    -0.61
    meier
    -0.60
    POSITIVE LOGITS
     tolerate
    0.78
     necessarily
    0.76
     afford
    0.72
     exceed
    0.70
    icable
    0.68
     tolerated
    0.68
    ices
    0.67
     resist
    0.67
     contain
    0.67
     duplicate
    0.63
    Activations Density 0.017%

    No Known Activations