INDEX

Explanations

numbers associated with codes or identifiers

oai_token-act-pair · gpt-3.5-turbo

the presence of specific formatting or structure, particularly related to sections or attributions in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ingen

-0.76

perse

-0.73

ppelin

-0.67

 Dise

-0.65

hold

-0.64

 Micha

-0.63

doms

-0.62

vous

-0.59

hyd

-0.59

haven

-0.59

POSITIVE LOGITS

ICAN

1.17

hetically

0.97

RON

0.96

rition

0.94

terson

0.94

rix

0.91

TERN

0.90

rice

0.90

itudes

0.90

RIC

0.90

Activations Density 0.021%

numbers associated with codes or identifiers

the presence of specific formatting or structure, particularly related to sections or attributions in a text

No Comments

No Known Activations