© 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. 10-RES-JB
    11. 17324
    Prev
    Next
    INDEX
    Explanations

    terms related to time-consuming tasks and efforts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to efficiency and cost savings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cola
    -0.74
    stasy
    -0.72
    ocent
    -0.69
     Positive
    -0.69
    apons
    -0.68
    soType
    -0.67
    haps
    -0.66
    ected
    -0.66
    gewater
    -0.66
    apor
    -0.65
    POSITIVE LOGITS
     tedious
    1.37
     hassle
    1.34
     costly
    1.33
     cumbersome
    1.27
     expense
    1.25
     cumbers
    1.21
     overhead
    1.19
     expensive
    1.18
     costs
    1.17
     burdens
    1.14
    Activations Density 0.636%

    No Known Activations