© 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. 4-RES-JB
    11. 22411
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive opinions or feedback

    oai_token-act-pair · gpt-3.5-turbo

    positive assessments of experiences or objects

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

    No Comments

    Negative Logits
    pec
    -0.70
     contracted
    -0.68
     forcefully
    -0.66
     consent
    -0.66
     prematurely
    -0.65
    Correct
    -0.64
     separately
    -0.64
     termination
    -0.63
     contingency
    -0.62
     mandated
    -0.62
    POSITIVE LOGITS
    Reviewer
    0.83
     congr
    0.79
     Ridley
    0.77
     âĿ
    0.76
     ðŁĻĤ
    0.70
    ipeg
    0.70
     versatility
    0.70
     accol
    0.70
    ðŁij
    0.69
    smanship
    0.69
    Activations Density 0.745%

    No Known Activations