INDEX

Explanations

phrases related to specific events or actions

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of work or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

PU

-0.83

 princ

-0.71

Uni

-0.70

 Chap

-0.69

 decl

-0.68

 COMP

-0.67

CHR

-0.67

GP

-0.67

dh

-0.66

 dist

-0.66

POSITIVE LOGITS

ing

1.38

ed

1.23

ings

1.20

ership

1.11

edIn

1.02

ers

1.02

age

0.99

edly

0.96

able

0.96

ation

0.96

Activations Density 0.269%

phrases related to specific events or actions

words related to various forms of work or actions

No Comments

No Known Activations