© 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. 7571
    Prev
    Next
    INDEX
    Explanations

    phrases related to encountering errors and trying again

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the act of trying again after an error

    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
    ELD
    -0.58
     Galile
    -0.58
    plates
    -0.57
    cult
    -0.53
    ELY
    -0.53
    bey
    -0.53
    Hop
    -0.52
     Matter
    -0.51
    matter
    -0.51
     proceedings
    -0.51
    POSITIVE LOGITS
    interstitial
    0.86
    Cola
    0.84
    olicy
    0.66
     later
    0.65
    nir
    0.64
     è£ıè¦ļéĨĴ
    0.62
     comma
    0.62
     recycle
    0.61
     Later
    0.61
    dra
    0.60
    Activations Density 0.014%

    No Known Activations