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. 3-RES-JB
    6. 2059
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of maturation or saturation

    oai_token-act-pair · gpt-3.5-turbo

    words related to the process or concept of 'nature' or 'natural.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.85
    Sil
    -0.67
    Assembly
    -0.63
    Companies
    -0.60
     awoken
    -0.60
    Bridge
    -0.60
     edible
    -0.58
     Bain
    -0.58
    OWS
    -0.58
     gracious
    -0.58
    POSITIVE LOGITS
    atur
    1.11
    ater
    0.96
    mble
    0.96
    ility
    0.95
    aters
    0.94
    isen
    0.94
    atism
    0.93
    aten
    0.92
    ating
    0.92
    eness
    0.90
    Activations Density 0.009%

    No Known Activations