INDEX

Explanations

specific names or entities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals involved in a narrative or incident

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ranked

-0.79

wikipedia

-0.73

aternity

-0.72

duc

-0.70

naire

-0.69

mount

-0.69

çĦ

-0.68

ĸļ

-0.68

raising

-0.66

ebook

-0.65

POSITIVE LOGITS

 Toro

1.16

 Strait

0.80

ettel

0.75

ulla

0.75

 Elliot

0.73

 Lumpur

0.73

inez

0.73

 peppers

0.73

-------

0.72

IELD

0.70

Activations Density 0.011%

specific names or entities mentioned in the text

references to specific individuals involved in a narrative or incident

No Comments

No Known Activations