© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 5037
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or steps required to achieve a certain goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sequence of actions or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marine
    -0.76
    tex
    -0.70
    reens
    -0.68
    tty
    -0.67
     patio
    -0.65
    tch
    -0.65
    reath
    -0.64
    tu
    -0.63
    mob
    -0.63
    tur
    -0.61
    POSITIVE LOGITS
     Osw
    0.77
    awaru
    0.72
     è£ıè¦ļéĨĴ
    0.66
     recap
    0.65
    hea
    0.64
    ãĤ·ãĥ£
    0.62
    arate
    0.60
     Puzzles
    0.59
    İ
    0.58
    ppel
    0.58
    Activations Density 0.018%

    No Known Activations