INDEX

Explanations

names or terms related to a specific character, possibly from a book or movie, that seems to have a protective or consuming nature

oai_token-act-pair · gpt-3.5-turbo

proper names, specifically those related to individuals and their roles or attributes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.78

ITNESS

-0.77

AVG

-0.72

Interstitial

-0.69

 Holmes

-0.69

 Corpus

-0.66

ALS

-0.65

 Berkshire

-0.65

çĽ

-0.65

POSITIVE LOGITS

 Drag

1.17

Drag

0.99

glers

0.97

Ã³n

0.94

oon

0.94

hett

0.93

achel

0.88

ged

0.88

otten

0.87

assi

0.87

Activations Density 0.007%

names or terms related to a specific character, possibly from a book or movie, that seems to have a protective or consuming nature

proper names, specifically those related to individuals and their roles or attributes

No Known Activations