INDEX

Explanations

expressions or symbols

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific symbol or character representative of formatting or separation in text

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

ppard

-0.79

interstitial

-0.76

wagen

-0.70

 granite

-0.68

ba

-0.68

eper

-0.67

foc

-0.67

 nuts

-0.67

 marble

-0.64

 levers

-0.63

POSITIVE LOGITS

————

1.15

————————————————

0.96

————————

0.93

——

0.83

 Advertisement

0.82

ĸļ

0.78

actionDate

0.76

advertisement

0.76

 Reporter

0.76

ADVERTISEMENT

0.75

Activations Density 0.049%

expressions or symbols

occurrences of a specific symbol or character representative of formatting or separation in text

No Comments

No Known Activations