INDEX

Explanations

mentions of military ranks, specifically "Lt" (Lieutenant)

oai_token-act-pair · gpt-3.5-turbo

references to military ranks and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

FORE

-0.81

âĶģ

-0.79

Offline

-0.78

å¥³

-0.78

anwhile

-0.76

BOOK

-0.76

theless

-0.76

tumblr

-0.76

 Marketable

-0.75

 Referred

-0.69

POSITIVE LOGITS

Lt

0.96

Lt

0.91

ue

0.80

idy

0.80

Col

0.77

eter

0.77

Sgt

0.77

una

0.76

usal

0.74

Maj

0.74

Activations Density 0.012%

mentions of military ranks, specifically "Lt" (Lieutenant)

references to military ranks and titles

No Comments

No Known Activations