© 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. 8-RES-JB
    11. 23447
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Dom" primarily in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Dom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    packing
    -0.84
     arrows
    -0.65
     arrow
    -0.65
    keeper
    -0.63
    UGH
    -0.63
    WAYS
    -0.62
     seeker
    -0.62
    fields
    -0.61
    gow
    -0.61
    forms
    -0.60
    POSITIVE LOGITS
    inant
    1.24
    ino
    1.16
    estic
    1.14
    ains
    1.09
    ination
    1.05
    inal
    1.02
    aine
    1.00
    inating
    0.98
    inations
    0.90
    orph
    0.89
    Activations Density 0.040%

    No Known Activations