INDEX

Explanations

terms related to military equipment and operations

oai_token-act-pair · gpt-3.5-turbo

letters or symbols that are indicative of specific categories or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤ©

-0.75

ãĥĻ

-0.66

--------------------------------------------------------

-0.63

 Costa

-0.62

 unsupported

-0.61

 speed

-0.58

 credibility

-0.56

 familiar

-0.55

 Penet

-0.55

 func

-0.54

POSITIVE LOGITS

atcher

0.85

ZI

0.78

ZE

0.74

OPS

0.74

HS

0.73

zl

0.72

xon

0.71

tn

0.70

RL

0.70

Activations Density 0.185%

terms related to military equipment and operations

letters or symbols that are indicative of specific categories or identifiers

No Comments

No Known Activations