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. 11-RES-JB
    6. 9549
    Prev
    Next
    INDEX
    Explanations

    messages related to personal development and empowerment

    oai_token-act-pair · gpt-3.5-turbo

    motivational language focused on self-improvement and personal agency

    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
    —"
    -1.02
    ãĥīãĥ©
    -0.86
    Enlarge
    -0.84
    "—
    -0.73
    )—
    -0.68
    "]
    -0.68
    ];
    -0.67
    Å«
    -0.66
    Åį
    -0.66
     âĢķ
    -0.65
    POSITIVE LOGITS
     thats
    1.25
     alot
    1.24
     ie
    1.21
     but
    1.18
     haha
    1.18
     lol
    1.15
     whereas
    1.15
     tho
    1.12
     BUT
    1.12
     doesnt
    1.10
    Activations Density 1.496%

    No Known Activations