INDEX

Explanations

mentions of or references to detention facilities or centers

oai_token-act-pair · gpt-3.5-turbo

references to detention facilities and the conditions surrounding them

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

chrom

-0.68

clerosis

-0.66

ãĥ£

-0.64

bold

-0.64

Roll

-0.63

soDeliveryDate

-0.63

hl

-0.62

ocaly

-0.61

raviolet

-0.61

odic

-0.61

POSITIVE LOGITS

 detention

0.97

rooms

0.85

 detainees

0.85

 detain

0.84

 detained

0.81

anamo

0.79

 facilities

0.76

ainers

0.76

rans

0.74

 Facility

0.72

Activations Density 0.023%

mentions of or references to detention facilities or centers

references to detention facilities and the conditions surrounding them

No Comments

No Known Activations