© 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. 327
    Prev
    Next
    INDEX
    Explanations

    economic and statistical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical measurements and economic indicators

    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
     acad
    -0.84
    ooks
    -0.74
    Ops
    -0.66
     dismant
    -0.66
    thren
    -0.65
    lov
    -0.64
    Brave
    -0.64
    Works
    -0.63
    ĪĴ
    -0.63
    Ark
    -0.63
    POSITIVE LOGITS
     measurement
    1.25
     estimation
    1.22
     fluct
    1.18
     proportional
    1.13
     measured
    1.12
     percentage
    1.10
     computed
    1.09
     calculated
    1.05
     determining
    1.05
     coefficient
    1.04
    Activations Density 0.607%

    No Known Activations