INDEX

Explanations

specific actions or objects related to physical altercations or conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of specific objects, individuals, or significant topics within a narrative

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.53

¿½

-0.52

 Emin

-0.51

 Leilan

-0.49

 confir

-0.48

 conclud

-0.47

 surpr

-0.46

 Rampage

-0.46

 Aires

-0.45

ãĥ´

-0.44

POSITIVE LOGITS

 badge

0.56

 onto

0.52

 hostage

0.48

 button

0.45

 Seal

0.45

pes

0.45

 reins

0.45

onto

0.45

 curse

0.45

 securely

0.44

Activations Density 1.656%

specific actions or objects related to physical altercations or conflicts

mentions of specific objects, individuals, or significant topics within a narrative

No Comments

No Known Activations