INDEX

Explanations

references to specific entities or terms within a structured environment

oai_token-act-pair · gpt-3.5-turbo

references to prestigious events, locations, or accolades

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

rawdownloadcloneembedreportprint

-0.81

pod

-0.68

bush

-0.66

Äĩ

-0.63

 Born

-0.62

less

-0.61

 Aber

-0.61

CAP

-0.60

 STATS

-0.60

 Calls

-0.60

POSITIVE LOGITS

ioxide

1.07

itsu

0.78

estyles

0.78

ĵĺ

0.77

 charact

0.74

ppers

0.74

 livest

0.73

 mathemat

0.73

irts

0.71

asion

0.71

Activations Density 0.288%

references to specific entities or terms within a structured environment

references to prestigious events, locations, or accolades

No Comments

No Known Activations