INDEX

Explanations

phrases related to actions involving technology or information

oai_token-act-pair · gpt-3.5-turbo

expressions of decision-making or careful consideration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

illard

-0.78

older

-0.72

rongh

-0.63

 Sleeping

-0.63

 idol

-0.63

SEE

-0.62

 Reincarnated

-0.61

itta

-0.60

 favorite

-0.60

oded

-0.59

POSITIVE LOGITS

_.

0.77

 stroke

0.75

Ò

0.73

 strokes

0.73

tails

0.72

HCR

0.71

 persuasion

0.70

 flick

0.70

 intervals

0.69

dding

0.68

Activations Density 0.646%

phrases related to actions involving technology or information

expressions of decision-making or careful consideration

No Comments

No Known Activations