INDEX

Explanations

phrases indicating completion or accomplishment

oai_token-act-pair · gpt-3.5-turbo

pronouns and verbs that indicate actions or capabilities related to doing something

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

 Cabin

-0.68

 Craw

-0.63

 Wide

-0.61

Ruk

-0.59

XT

-0.59

 Bunker

-0.59

 Upper

-0.58

ixels

-0.58

 Toggle

-0.58

cv

-0.57

POSITIVE LOGITS

own

0.92

 lawfully

0.87

self

0.78

selves

0.77

 pretended

0.74

areth

0.72

 predec

0.72

OWN

0.71

 intended

0.68

 normally

0.68

Activations Density 0.202%

phrases indicating completion or accomplishment

pronouns and verbs that indicate actions or capabilities related to doing something

No Comments

No Known Activations