INDEX

Explanations

phrases related to historical events or locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Great" in various historic contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isSpecialOrderable

-0.87

earchers

-0.84

ople

-0.76

qqa

-0.75

Downloadha

-0.73

ograp

-0.73

utical

-0.72

ktop

-0.69

uably

-0.69

VICE

-0.68

POSITIVE LOGITS

 Lakes

0.85

 Recession

0.84

 Basin

0.82

sword

0.81

batch

0.81

 Divide

0.79

 Barrier

0.77

 Plains

0.76

 Treaty

0.75

ness

0.75

Activations Density 0.013%

phrases related to historical events or locations

occurrences of the term "Great" in various historic contexts

No Comments

No Known Activations