INDEX

Explanations

phrases related to legal actions and consequences

oai_token-act-pair · gpt-3.5-turbo

references to jail time and imprisonment

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

yip

-1.07

omorphic

-0.81

Ðº

-0.78

Ò

-0.75

é¾įåĸļå£«

-0.75

 guiActiveUnfocused

-0.73

å§«

-0.71

ãĤ§

-0.71

soDeliveryDate

-0.71

sonian

-0.71

POSITIVE LOGITS

 Detention

0.86

 Rehab

0.85

 Sergeant

0.84

 interrogation

0.81

 detention

0.81

 psychiatric

0.78

 confiscated

0.78

 interrogated

0.77

 Deaths

0.76

 inmate

0.74

Activations Density 0.502%

phrases related to legal actions and consequences

references to jail time and imprisonment

No Comments

No Known Activations