© 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. 7-RES-JB
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    Keywords or phrases related to a specific location or identity, possibly an abbrevation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Id" followed by numbers, indicating identification codes or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saunders
    -0.74
     thinner
    -0.70
     Remastered
    -0.70
    toe
    -0.69
     guiActiveUnfocused
    -0.69
     Kraken
    -0.63
    feeding
    -0.62
    ttes
    -0.60
    OUP
    -0.60
    ¶ħ
    -0.59
    POSITIVE LOGITS
    aho
    1.34
    entity
    1.30
    iom
    1.29
    leness
    1.25
    yll
    1.24
    iots
    1.22
    ividual
    1.17
    iosyncr
    1.15
    iop
    1.14
    iotic
    1.10
    Activations Density 0.027%

    No Known Activations