© 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. 3935
    Prev
    Next
    INDEX
    Explanations

    phrases related to prioritization of personal interests over collective interests, possibly warning against it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "respond."

    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
     Syri
    -0.67
     Hels
    -0.63
     Fas
    -0.63
    Ü
    -0.62
    lain
    -0.62
    ernaut
    -0.61
    maid
    -0.61
    dies
    -0.60
    alsh
    -0.59
    ieth
    -0.59
    POSITIVE LOGITS
    =#
    0.83
    rant
    0.79
    anchester
    0.67
    peria
    0.66
     Publication
    0.66
     teasing
    0.66
    otti
    0.66
    Ħ¢
    0.65
    Magikarp
    0.64
     âĶľ
    0.63
    Activations Density 0.000%

    No Known Activations