INDEX

Explanations

verbs in the past tense related to prior planning or intention

oai_token-act-pair · gpt-3.5-turbo

instances of the word "planned."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ienced

-0.81

ĪĴ

-0.78

upon

-0.76

ysis

-0.74

bour

-0.71

assi

-0.71

gars

-0.70

Reviewer

-0.70

aina

-0.70

yards

-0.70

POSITIVE LOGITS

 Parenthood

1.30

paren

0.96

 pregnancies

0.93

obs

0.83

 gestation

0.78

escape

0.77

 meals

0.76

 trips

0.76

 rollout

0.75

¶

0.74

Activations Density 0.022%

verbs in the past tense related to prior planning or intention

instances of the word "planned."

No Comments

No Known Activations