© 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. 8354
    Prev
    Next
    INDEX
    Explanations

    short forms or acronyms ending with "SL"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regulatory agencies or bodies

    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
     Samar
    -0.71
    tainment
    -0.66
    ãĥ¡
    -0.63
    ria
    -0.62
    raising
    -0.61
    ãĥĨãĤ£
    -0.60
    gerald
    -0.60
    Downloadha
    -0.59
     comfort
    -0.59
    ãĤ¹ãĥĪ
    -0.58
    POSITIVE LOGITS
    ength
    0.96
    ASH
    0.96
    OTS
    0.90
    avery
    0.90
    OW
    0.88
    SL
    0.88
    arge
    0.87
    anguage
    0.87
    ibrary
    0.84
    ash
    0.81
    Activations Density 0.002%

    No Known Activations