© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4363
    Prev
    Next
    INDEX
    Explanations

    different types of ladders

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to hierarchical structures and relationships

    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
    taboola
    -0.71
    ĵĺ
    -0.70
    tesy
    -0.65
    ¶ħ
    -0.64
    NetMessage
    -0.63
     HuffPost
    -0.58
     Hollywood
    -0.58
    oba
    -0.53
    laus
    -0.53
     Approximately
    -0.52
    POSITIVE LOGITS
     rul
    0.70
    ultimate
    0.67
    worthiness
    0.64
    hess
    0.63
    scape
    0.63
     destro
    0.61
    eers
    0.60
    icular
    0.60
     sucked
    0.60
     cutter
    0.59
    Activations Density 1.737%

    No Known Activations