© 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. 7-RES-JB
    11. 24172
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical values or ratings

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "zero" ratings, days, and sums in relation to economic and financial contexts

    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
    ournals
    -0.72
     widest
    -0.69
    ĸļ
    -0.68
    amel
    -0.63
    SEA
    -0.62
    thus
    -0.62
    artifacts
    -0.60
    gypt
    -0.59
    TAIN
    -0.59
    SPONSORED
    -0.59
    POSITIVE LOGITS
    rencies
    0.70
    olerance
    0.70
     particles
    0.69
    energy
    0.68
     sqor
    0.64
     particle
    0.64
    ndra
    0.62
    utonium
    0.61
    gravity
    0.61
    zero
    0.61
    Activations Density 0.140%

    No Known Activations