© 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. 24338
    Prev
    Next
    INDEX
    Explanations

    specific descriptions regarding a situation or surroundings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "It was" used to describe various situations or states

    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
     Critics
    -0.73
    derived
    -0.72
    ribe
    -0.71
    è¦ļéĨĴ
    -0.71
    riber
    -0.70
    endants
    -0.69
     subscrib
    -0.68
    mson
    -0.67
    responsible
    -0.67
    bi
    -0.67
    POSITIVE LOGITS
     raining
    1.49
     dusk
    1.24
     midday
    1.21
     rainy
    1.18
     chilly
    1.18
     surreal
    1.17
     noon
    1.12
     nighttime
    1.09
     sunny
    1.07
     unbearable
    1.06
    Activations Density 0.191%

    No Known Activations