INDEX

Explanations

pronouns followed by a verb indicating an action

oai_token-act-pair · gpt-3.5-turbo

the pronoun "We."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

LSD

-0.66

quo

-0.65

bud

-0.64

INGTON

-0.63

REDACTED

-0.63

onies

-0.60

 Publication

-0.60

 Chad

-0.58

 steroids

-0.57

cum

-0.57

POSITIVE LOGITS

asel

1.05

IRD

0.98

're

0.98

ighed

0.95

bsite

0.95

selves

0.94

've

0.90

chwitz

0.87

ldon

0.87

'll

0.86

Activations Density 0.107%

pronouns followed by a verb indicating an action

the pronoun "We."

No Comments

No Known Activations