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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 2370
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events happening in a sequence or process

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of instructions or actions involving continuity and maintaining connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resy
    -0.71
    ithe
    -0.70
    thing
    -0.69
    recy
    -0.68
    sometimes
    -0.67
    farious
    -0.67
    later
    -0.66
    sequent
    -0.66
    igmatic
    -0.65
    illusion
    -0.65
    POSITIVE LOGITS
     Prediction
    0.67
     Ranking
    0.64
     202
    0.60
     Ranked
    0.59
     FOX
    0.57
     (@
    0.57
     WATCH
    0.56
     Rutherford
    0.56
     retweet
    0.55
     AMERICA
    0.55
    Activations Density 1.242%

    No Known Activations