© 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. 11-RES-JB
    11. 9947
    Prev
    Next
    INDEX
    Explanations

    phrases related to successful or impactful actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "make" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.88
    hood
    -0.71
    ãĥİ
    -0.71
     Ples
    -0.70
    tg
    -0.68
    æ©Ł
    -0.66
    PLIED
    -0.65
    thouse
    -0.64
    andowski
    -0.64
    pour
    -0.64
    POSITIVE LOGITS
     strides
    1.25
     mistakes
    1.01
     adjustments
    1.00
     sacrifices
    0.96
     plays
    0.89
     sure
    0.89
     excuses
    0.88
     saves
    0.84
     noises
    0.82
    hift
    0.81
    Activations Density 0.073%

    No Known Activations