© 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. 6-RES-JB
    11. 19691
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the city of Brest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bre" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iating
    -0.81
     Fired
    -0.77
    iated
    -0.73
    ONES
    -0.73
    å°Ĩ
    -0.71
    uality
    -0.70
     guiActiveUnfocused
    -0.68
    AGES
    -0.68
     relief
    -0.67
    iants
    -0.65
    POSITIVE LOGITS
    thren
    1.21
    akers
    1.10
    acher
    1.07
    aks
    1.07
    aker
    1.04
    aches
    1.00
    eding
    0.98
    lyn
    0.98
    cker
    0.97
    igh
    0.97
    Activations Density 0.010%

    No Known Activations