© 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. 8-RES-JB
    11. 6835
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating the impact or effect of various actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant effects or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owship
    -0.74
    hooting
    -0.72
    bys
    -0.64
    Reviewer
    -0.60
     Fighting
    -0.60
    bis
    -0.60
     Lands
    -0.59
    archives
    -0.58
    pointers
    -0.58
    Train
    -0.57
    POSITIVE LOGITS
     implications
    1.14
     significance
    1.11
     effect
    1.08
     ramifications
    1.07
     reperc
    1.05
     impact
    1.04
     repercussions
    1.04
    tones
    1.00
     origins
    0.99
     ripple
    0.99
    Activations Density 0.297%

    No Known Activations