Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3670
    Prev
    Next
    INDEX
    Explanations

    word stems related to actions or processes involving a twisting or turning motion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spiraling or downward trends

    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
    Hispanic
    -0.70
     Corpus
    -0.69
    houses
    -0.68
    STR
    -0.66
     relics
    -0.62
     Defender
    -0.60
     Mayweather
    -0.60
     Vict
    -0.59
     Samar
    -0.59
     Nou
    -0.58
    POSITIVE LOGITS
    aling
    1.31
    alling
    1.25
    aled
    1.16
    atory
    1.06
    ators
    1.01
    als
    1.00
    atorial
    0.99
    acle
    0.98
    ationally
    0.98
    ited
    0.96
    Activations Density 0.045%

    No Known Activations