INDEX

Explanations

instances of the word "chose"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "chose" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.88

ptoms

-0.72

ijk

-0.69

oun

-0.69

bley

-0.68

qv

-0.67

emic

-0.66

aura

-0.65

Net

-0.65

peria

-0.64

POSITIVE LOGITS

 wisely

0.87

 chose

0.84

 chooses

0.80

 chosen

0.79

 randomly

0.76

 choose

0.74

 choosing

0.73

 choice

0.71

axe

0.67

 Wise

0.66

Activations Density 0.043%

instances of the word "chose"

instances of the word "chose" and its variations

No Comments

No Known Activations