© 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. 2-RES-JB
    11. 24104
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term - "bar"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "bar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dangerous
    -0.73
     Gutenberg
    -0.70
     MO
    -0.70
    EEE
    -0.70
     EntityItem
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    URES
    -0.67
     CLSID
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
     partName
    -0.66
    POSITIVE LOGITS
    becue
    1.16
    bar
    1.14
    bell
    1.09
    celona
    1.07
    bara
    0.99
    itone
    0.91
    anski
    0.83
    rier
    0.82
    rel
    0.82
    flies
    0.82
    Activations Density 0.009%

    No Known Activations