© 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. 508
    Prev
    Next
    INDEX
    Explanations

    phrases related to estimates or estimations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numerical estimates and measurements

    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
    NetMessage
    -0.89
    woods
    -0.83
    feeding
    -0.80
    Interstitial
    -0.80
    wood
    -0.72
    ModLoader
    -0.70
    ktop
    -0.68
    artney
    -0.66
    bley
    -0.65
    catching
    -0.65
    POSITIVE LOGITS
     estimates
    1.13
     estimate
    1.13
    imates
    1.04
    imate
    0.88
     estimating
    0.86
     Estimates
    0.85
     estim
    0.83
     estimation
    0.81
     forecasts
    0.80
     estimated
    0.78
    Activations Density 0.018%

    No Known Activations