Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 12325
    Prev
    Next
    INDEX
    Explanations

    information related to human evolution and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the relationship between humans and other living beings and their environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spotlight
    -0.83
    raine
    -0.78
     Cannes
    -0.78
     Bulg
    -0.78
    price
    -0.76
    District
    -0.76
    soDeliveryDate
    -0.75
    Magazine
    -0.74
    ticket
    -0.74
     Signature
    -0.73
    POSITIVE LOGITS
     humans
    1.56
     apes
    1.53
    humans
    1.45
     Homo
    1.43
     sentient
    1.43
     primates
    1.41
     organisms
    1.40
     mammals
    1.39
     humankind
    1.38
     Humans
    1.37
    Activations Density 0.760%

    No Known Activations