© 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. 3-RES-JB
    11. 8878
    Prev
    Next
    INDEX
    Explanations

    words related to changing or modifying something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "alter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ
    -0.74
    DragonMagazine
    -0.73
     Citation
    -0.73
    Simple
    -0.69
    Supported
    -0.68
    ILLE
    -0.68
    True
    -0.68
    Phones
    -0.67
    ETF
    -0.67
    Pred
    -0.67
    POSITIVE LOGITS
     alters
    0.93
     alter
    0.86
     costumes
    0.84
     wrench
    0.84
     havoc
    0.80
     wig
    0.79
     ego
    0.78
    atile
    0.77
     altering
    0.76
    ments
    0.73
    Activations Density 0.015%

    No Known Activations