© 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. 18726
    Prev
    Next
    INDEX
    Explanations

    objects or items that are associated with specific functions or meanings

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns, particularly those related to objects, concepts, or tools

    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
    noxious
    -0.64
     Legislative
    -0.55
     Balanced
    -0.54
    cffff
    -0.54
     volatile
    -0.52
    selves
    -0.51
     endogenous
    -0.50
     ACPI
    -0.49
    utenberg
    -0.49
     Latest
    -0.49
    POSITIVE LOGITS
    less
    0.68
    able
    0.66
    aments
    0.60
    ings
    0.59
    fuck
    0.58
    age
    0.55
    watch
    0.55
    book
    0.55
    pipe
    0.55
    marks
    0.54
    Activations Density 0.742%

    No Known Activations