INDEX

Explanations

descriptions or instructions related to displaying visual content

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "show" and its variations, indicating a focus on visual content or presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pton

-0.90

inventoryQuantity

-0.80

youtube

-0.73

Ãª

-0.71

iche

-0.69

EEE

-0.68

aceutical

-0.67

unia

-0.66

vice

-0.65

NOTE

-0.65

POSITIVE LOGITS

how

0.95

runners

0.93

ered

0.93

biz

0.91

rooms

0.89

 flashes

0.89

downs

0.88

 prominently

0.88

 signs

0.86

 similarities

0.82

Activations Density 0.066%

descriptions or instructions related to displaying visual content

occurrences of the word "show" and its variations, indicating a focus on visual content or presentations

No Comments

No Known Activations