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. 2-RES-JB
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a location called Rox or Rosa

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and people associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.73
    iatus
    -0.73
    gency
    -0.72
    ij士
    -0.71
    ®
    -0.71
    forestation
    -0.70
    ship
    -0.69
    nered
    -0.69
    rar
    -0.69
    atus
    -0.69
    POSITIVE LOGITS
     Adin
    0.95
    helle
    0.83
    oche
    0.81
    accompan
    0.77
     Nation
    0.74
    otta
    0.70
    uberty
    0.69
    hap
    0.67
    asso
    0.66
    oshenko
    0.66
    Activations Density 0.033%

    No Known Activations