© 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. 0-RES-JB
    11. 2892
    Prev
    Next
    INDEX
    Explanations

    words related to television episodes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of television episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isse
    -0.67
     CONS
    -0.66
    hene
    -0.65
    cision
    -0.65
    oto
    -0.64
     Overse
    -0.63
    vi
    -0.63
     Equality
    -0.62
    itute
    -0.61
    yer
    -0.61
    POSITIVE LOGITS
     episodes
    3.69
     episode
    2.43
    episode
    2.27
    isodes
    2.08
    Episode
    1.90
     Episode
    1.88
     chapters
    1.66
     bouts
    1.60
     flashbacks
    1.60
     epis
    1.59
    Activations Density 0.020%

    No Known Activations