INDEX

Explanations

adverbs that describe frequency of actions or events

oai_token-act-pair · gpt-3.5-turbo

adverbial forms indicating frequency or manner

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

arth

-0.98

ipedia

-0.86

arna

-0.78

wikipedia

-0.73

href

-0.73

yp

-0.72

 Metall

-0.72

trap

-0.71

ARI

-0.71

wright

-0.71

POSITIVE LOGITS

 equivalents

0.82

 endeavour

0.82

²¾

0.82

 visitation

0.81

 endeavor

0.80

 continuation

0.79

 custody

0.78

 affairs

0.78

 pursuits

0.78

 communication

0.77

Activations Density 0.094%

adverbs that describe frequency of actions or events

adverbial forms indicating frequency or manner

No Comments

No Known Activations