© 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. 21352
    Prev
    Next
    INDEX
    Explanations

    phrases related to change or development

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "become."

    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
    ength
    -0.75
    orsi
    -0.69
    UGH
    -0.66
    shoot
    -0.65
    enary
    -0.65
    inarily
    -0.64
    merga
    -0.64
    joy
    -0.63
    pta
    -0.62
    brow
    -0.62
    POSITIVE LOGITS
     extinct
    1.11
     clearer
    1.11
     increasingly
    1.10
     obsolete
    1.08
     entangled
    1.07
     commonplace
    1.03
     progressively
    1.01
     apparent
    1.00
     unman
    1.00
     irrelevant
    1.00
    Activations Density 0.062%

    No Known Activations