INDEX

Explanations

phrases indicating the continuation or progression of a narrative or report

oai_token-act-pair · gpt-3.5-turbo

statements or claims made in reports and documents

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

ixie

-0.63

urity

-0.60

pected

-0.59

Zone

-0.58

omorphic

-0.58

joice

-0.58

 footing

-0.58

Xan

-0.57

ustomed

-0.57

oding

-0.57

POSITIVE LOGITS

 acronym

0.69

:]

0.68

:[

0.67

 moot

0.67

 cris

0.64

 crochet

0.58

 summar

0.58

urst

0.58

broad

0.57

 broadly

0.56

Activations Density 0.526%

phrases indicating the continuation or progression of a narrative or report

statements or claims made in reports and documents

No Comments

No Known Activations