© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    the concept of something being "real" or "actual"

    oai_token-act-pair · gpt-3.5-turbo

    terms that convey a sense of reality or truthfulness

    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
    cius
    -0.80
     Beware
    -0.78
    sometimes
    -0.73
    alian
    -0.73
    prone
    -0.70
    gypt
    -0.69
     beware
    -0.68
    VL
    -0.68
    ql
    -0.66
    clair
    -0.65
    POSITIVE LOGITS
     whatsoever
    1.24
     explanation
    1.00
     indication
    0.94
     distinction
    0.94
     reason
    0.93
     reperc
    0.89
     recourse
    0.89
     substantive
    0.86
     nor
    0.85
     excuse
    0.84
    Activations Density 0.164%

    No Known Activations