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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 4404
    Prev
    Next
    INDEX
    Explanations

    keywords related to technological advancements, such as "sequencing technologies" and "spectrum bands for 5G use."

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to modern technological advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    but
    -0.71
     But
    -0.67
    unless
    -0.67
     };
    -0.66
    ;}
    -0.66
     but
    -0.66
     except
    -0.62
    .;
    -0.62
    except
    -0.61
    ";
    -0.61
    POSITIVE LOGITS
    raq
    0.86
     intervened
    0.76
    »Ĵ
    0.74
     nonetheless
    0.68
    etheless
    0.68
    éŃĶ
    0.68
     convinced
    0.67
    âĢ
    0.67
     clarified
    0.66
     proved
    0.66
    Activations Density 0.686%

    No Known Activations