© 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. 4-RES-JB
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    terms related to financial value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of value or worth in a monetary context

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

    No Comments

    Negative Logits
    gdala
    -0.79
     Plain
    -0.74
     Pats
    -0.70
     Dogs
    -0.70
     Nou
    -0.68
     Neurolog
    -0.66
     Bliss
    -0.65
     Ribbon
    -0.65
     Aval
    -0.64
     Hazel
    -0.64
    POSITIVE LOGITS
    iness
    0.96
    ensing
    0.89
    ily
    0.87
     worth
    0.85
    folios
    0.82
    worth
    0.81
    otation
    0.81
    entin
    0.78
    ume
    0.77
    withstanding
    0.74
    Activations Density 0.012%

    No Known Activations