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. 8550
    Prev
    Next
    INDEX
    Explanations

    people or families moving from one location to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moved" and related concepts about relocation

    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
    iciency
    -0.75
    lime
    -0.71
     Digest
    -0.68
    pport
    -0.67
    omial
    -0.62
    onomy
    -0.60
     Curve
    -0.60
     Brach
    -0.60
    zing
    -0.58
    ipes
    -0.58
    POSITIVE LOGITS
     away
    1.06
     abroad
    1.04
     into
    1.04
     indoors
    1.03
     onto
    0.96
     inland
    0.96
     hither
    0.92
     farther
    0.90
     west
    0.87
     north
    0.87
    Activations Density 0.065%

    No Known Activations