INDEX

Explanations

instances of the word "turn"

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "turning" or changing situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

è¦ļéĨĴ

-0.96

ority

-0.62

BE

-0.62

icipated

-0.62

Story

-0.61

heon

-0.60

bour

-0.59

resh

-0.59

 Profile

-0.58

hess

-0.56

POSITIVE LOGITS

around

0.93

 inward

0.82

coat

0.82

 around

0.80

 heads

0.79

 away

0.74

 aside

0.73

 into

0.72

key

0.72

 tables

0.71

Activations Density 0.032%

instances of the word "turn"

phrases related to the concept of "turning" or changing situations

No Comments

No Known Activations