INDEX

Explanations

words or phrases related to large-scale incidents or catastrophes, particularly involving harm to multiple individuals

oai_token-act-pair · gpt-3.5-turbo

references to mass events or occurrences, especially those related to violence or disasters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nos

-0.78

BILITIES

-0.78

yssey

-0.75

thy

-0.75

thens

-0.74

mins

-0.73

tis

-0.73

uana

-0.71

shire

-0.68

ilk

-0.68

POSITIVE LOGITS

achusetts

1.47

 quantities

0.85

achus

0.85

 transit

0.78

aging

0.77

 exodus

0.76

 incarceration

0.72

eval

0.69

ablishment

0.69

 istg

0.68

Activations Density 0.016%

words or phrases related to large-scale incidents or catastrophes, particularly involving harm to multiple individuals

references to mass events or occurrences, especially those related to violence or disasters

No Comments

No Known Activations