INDEX

Explanations

phrases that signal a change of topic or a new direction in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Well" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omore

-0.65

illary

-0.61

adding

-0.60

ËĪ

-0.60

rift

-0.59

central

-0.59

aded

-0.59

acist

-0.58

kefeller

-0.58

Roaming

-0.57

POSITIVE LOGITS

 yeah

0.95

 hello

0.94

 guess

0.93

 prest

0.93

 luckily

0.84

ington

0.83

esley

0.82

 congratulations

0.79

 done

0.78

Activations Density 0.032%

phrases that signal a change of topic or a new direction in the text

instances of the word "Well" in various contexts

No Comments

No Known Activations