INDEX

Explanations

words related to selecting or making choices

oai_token-act-pair · gpt-3.5-turbo

instances of the word "choose" and its variations, indicating decisions or selections made by subjects

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

brance

-0.90

uum

-0.72

ijk

-0.71

igi

-0.68

Net

-0.68

qv

-0.68

urst

-0.64

Que

-0.64

ilitating

-0.64

clad

-0.63

POSITIVE LOGITS

 chooses

0.90

 chose

0.88

 wisely

0.82

 chosen

0.82

 ACTIONS

0.81

 choose

0.78

axe

0.75

 choices

0.73

 choosing

0.71

rawdownloadcloneembedreportprint

0.70

Activations Density 0.038%

words related to selecting or making choices

instances of the word "choose" and its variations, indicating decisions or selections made by subjects

No Comments

No Known Activations