INDEX

Explanations

phrases related to personal safety and security

oai_token-act-pair · gpt-3.5-turbo

concerns and references related to personal safety and protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

sonian

-0.75

nant

-0.72

 phys

-0.71

REE

-0.70

named

-0.68

urally

-0.68

meta

-0.68

etically

-0.65

 sugg

-0.65

quartered

-0.65

POSITIVE LOGITS

 refuge

0.78

angering

0.78

 havens

0.74

rieve

0.72

cffff

0.71

 largeDownload

0.70

 exits

0.70

peace

0.69

Lago

0.69

raints

0.69

Activations Density 0.101%

phrases related to personal safety and security

concerns and references related to personal safety and protection

No Comments

No Known Activations