INDEX

Explanations

occurrences where a related adverb follows a noun

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

âĿ

-0.85

encies

-0.79

ontent

-0.78

alties

-0.77

enance

-0.76

uez

-0.71

andon

-0.71

mares

-0.70

Ont

-0.70

[/

-0.69

POSITIVE LOGITS

 standalone

1.06

 result

1.03

 reminder

0.98

 consequence

0.93

 predictor

0.89

 precursor

0.89

 prerequisite

0.89

 gateway

0.88

 catalyst

0.87

 footnote

0.87

Activations Density 0.117%

occurrences where a related adverb follows a noun

instances of the article "a."

No Comments

No Known Activations