© 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. 17350
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions or authorizations

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating the absence of something

    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
     nonetheless
    -0.72
    iership
    -0.68
    elli
    -0.61
    knit
    -0.61
    wart
    -0.60
    minster
    -0.60
    grass
    -0.59
     Cathy
    -0.58
     nevertheless
    -0.58
    mill
    -0.58
    POSITIVE LOGITS
    vel
    0.94
     longer
    0.94
    ct
    0.90
    ise
    0.86
    zzle
    0.86
    except
    0.83
     matter
    0.83
    otrop
    0.81
    xious
    0.81
    vae
    0.79
    Activations Density 0.054%

    No Known Activations