INDEX

Explanations

words related to military or strategic activities, particularly those involving troops

oai_token-act-pair · gpt-3.5-turbo

terms related to troop and military references

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

Not in Any Lists

No Comments

Negative Logits

 Gateway

-0.72

lessly

-0.71

Orb

-0.66

FW

-0.63

AE

-0.61

 Title

-0.60

 Breath

-0.60

 TAMADRA

-0.60

Bye

-0.60

MD

-0.59

POSITIVE LOGITS

tro

1.29

atro

1.05

ophers

0.95

tsky

0.94

psey

0.94

chn

0.94

pha

0.94

pload

0.90

cer

0.89

otype

0.88

Activations Density 0.023%

words related to military or strategic activities, particularly those involving troops

terms related to troop and military references

No Comments

No Known Activations