Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17375
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "take a look" is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take a look."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cele
    -0.63
    cffff
    -0.60
    RIC
    -0.58
    theless
    -0.58
     Methods
    -0.57
    redict
    -0.57
    Staff
    -0.57
    GA
    -0.56
    Skill
    -0.56
    Est
    -0.54
    POSITIVE LOGITS
    ahead
    0.89
    finder
    0.81
    ression
    0.79
    ings
    0.78
    behind
    0.77
    atio
    0.76
    oscope
    0.73
    nings
    0.71
    enary
    0.71
    ãĤ¶
    0.70
    Activations Density 0.036%

    No Known Activations