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. 15891
    Prev
    Next
    INDEX
    Explanations

    instances of legal language or references to official documents

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and transition phrases in sentences

    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
    eco
    -0.76
    auri
    -0.70
    ruck
    -0.65
    eur
    -0.65
    eele
    -0.64
    uman
    -0.64
    ATT
    -0.60
    aled
    -0.60
    iam
    -0.59
    IER
    -0.58
    POSITIVE LOGITS
     nor
    2.00
    nor
    1.77
     preferring
    1.44
     Nor
    1.26
    Nor
    1.18
    yet
    1.18
     except
    1.15
     opting
    1.14
    Instead
    1.10
     Instead
    1.09
    Activations Density 0.296%

    No Known Activations