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. 4-RES-JB
    6. 3924
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations or programs with the initials "HA."

    oai_token-act-pair · gpt-3.5-turbo

    references to the National Housing Authority (NHA)

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

    No Comments

    Negative Logits
    ando
    -0.88
    orius
    -0.86
    naire
    -0.84
    ources
    -0.79
    ments
    -0.78
    itives
    -0.78
    ications
    -0.77
    ophone
    -0.77
     Sacrament
    -0.76
    ophon
    -0.74
    POSITIVE LOGITS
    ARP
    1.13
    VE
    1.13
    UGH
    0.98
    IL
    0.98
    WN
    0.97
    HAHA
    0.95
    HA
    0.92
    IR
    0.91
    OA
    0.88
    Proxy
    0.87
    Activations Density 0.014%

    No Known Activations