© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11329
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation or appraisal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to approval ratings or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĮ
    -0.74
     SHE
    -0.74
     Hicks
    -0.70
     Wi
    -0.65
     HELP
    -0.61
     Jessie
    -0.60
     Rudd
    -0.60
     chickens
    -0.60
     additionally
    -0.59
     feds
    -0.58
    POSITIVE LOGITS
    val
    4.51
    vals
    2.56
    VAL
    2.09
    Val
    1.76
     val
    1.56
    va
    1.40
    vale
    1.39
    eval
    1.35
     Val
    1.34
    valued
    1.33
    Activations Density 0.007%

    No Known Activations