INDEX

Explanations

phrases related to adding ingredients or substances into a mixture or container

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "into" and related phrases indicating action or transition

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

entimes

-0.85

yip

-0.82

gang

-0.72

zai

-0.72

die

-0.69

uten

-0.65

 gentleman

-0.63

thora

-0.63

cz

-0.62

uren

-0.62

POSITIVE LOGITS

 adulthood

0.95

 orbit

0.92

jected

0.81

jection

0.75

 Valhalla

0.69

 submission

0.69

itialized

0.67

ves

0.67

eligible

0.66

clusion

0.65

Activations Density 0.071%

phrases related to adding ingredients or substances into a mixture or container

occurrences of the word "into" and related phrases indicating action or transition

No Comments

No Known Activations