© 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. 2-RES-JB
    11. 2036
    Prev
    Next
    INDEX
    Explanations

    the concept of acceptance or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the word "okay" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ly
    -0.73
    hunt
    -0.73
    rylic
    -0.68
    hani
    -0.68
    rament
    -0.67
    iltration
    -0.67
    recy
    -0.66
    marine
    -0.66
    arcity
    -0.64
    hun
    -0.63
    POSITIVE LOGITS
     okay
    1.06
     ok
    0.95
     bye
    0.94
     OK
    0.93
     alright
    0.88
    lahoma
    0.88
     Okay
    0.84
     fine
    0.74
    AY
    0.74
     Alright
    0.73
    Activations Density 0.008%

    No Known Activations