INDEX

Explanations

first-person singular pronouns followed by verbs indicating past actions

oai_token-act-pair · gpt-3.5-turbo

first-person pronouns and expressions of conditionality or hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 srfAttach

-0.75

Reviewer

-0.72

 Binding

-0.68

 Whitman

-0.64

Leaks

-0.63

ãĥķãĤ©

-0.63

ãĥĥãĥī

-0.62

INGTON

-0.62

Balt

-0.59

POSITIVE LOGITS

'm

1.40

 guess

1.02

verson

0.96

am

0.95

've

0.93

 wish

0.85

zzo

0.84

 assume

0.83

 suppose

0.82

 wanna

0.82

Activations Density 0.079%

first-person singular pronouns followed by verbs indicating past actions

first-person pronouns and expressions of conditionality or hypothetical scenarios

No Comments

No Known Activations