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. 0-RES-JB
    6. 10694
    Prev
    Next
    INDEX
    Explanations

    instances where allocation of resources or responsibilities is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the distribution and management of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pil
    -0.72
    lie
    -0.69
    chu
    -0.68
     Strike
    -0.67
     Twist
    -0.66
     Siren
    -0.66
    Sil
    -0.66
    jah
    -0.66
    iri
    -0.65
    Strike
    -0.65
    POSITIVE LOGITS
     allocated
    3.08
     allocation
    3.08
     allocate
    3.05
     allocations
    2.93
     alloc
    2.69
    alloc
    2.18
    ocating
    1.88
     allotted
    1.84
     allot
    1.83
     quota
    1.22
    Activations Density 0.033%

    No Known Activations