INDEX

Explanations

phrases containing the word "there"

oai_token-act-pair · gpt-3.5-turbo

repetitions of the word "there"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 cogn

-0.62

 favour

-0.62

ME

-0.61

CJ

-0.59

 franc

-0.58

 tolerant

-0.56

cade

-0.56

 Franc

-0.55

uously

-0.55

icial

-0.55

POSITIVE LOGITS

abouts

1.31

upon

1.04

ngth

0.90

fore

0.84

geist

0.78

FORE

0.77

after

0.74

ichick

0.73

hovah

0.73

ain

0.69

Activations Density 0.130%

phrases containing the word "there"

repetitions of the word "there"

No Comments

No Known Activations