© 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. 8-RES-JB
    11. 22555
    Prev
    Next
    INDEX
    Explanations

    phrases related to outcomes and results

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating results or outcomes of actions

    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
    inventoryQuantity
    -0.76
    yi
    -0.74
    terday
    -0.73
    igraph
    -0.72
    addons
    -0.71
     aloud
    -0.67
    stan
    -0.67
    udi
    -0.63
    Enlarge
    -0.63
     mant
    -0.62
    POSITIVE LOGITS
     predictable
    0.98
     unequal
    0.81
     unpredictable
    0.77
    ãĥĩãĤ£
    0.76
     predictably
    0.74
     unsur
    0.73
    ãĥķãĤ©
    0.73
     disappointing
    0.73
     unsatisf
    0.71
     remarkable
    0.70
    Activations Density 0.138%

    No Known Activations