INDEX

Explanations

sentences or phrases that start with a specific symbol or punctuation, specifically ':' and '"'

oai_token-act-pair · gpt-3.5-turbo

textual content that includes quotes or statements

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

erker

-0.72

atcher

-0.67

 estim

-0.66

aukee

-0.66

ationally

-0.65

lisher

-0.64

 stalled

-0.63

agara

-0.63

igent

-0.62

arten

-0.62

POSITIVE LOGITS

"#

1.03

 "âĢ¦

0.89

Dear

0.86

"@

0.85

"(

0.76

"'

0.75

RIP

0.75

 Goodbye

0.74

"[

0.74

 "...

0.72

Activations Density 0.231%

sentences or phrases that start with a specific symbol or punctuation, specifically ':' and '"'

textual content that includes quotes or statements

No Comments

No Known Activations