INDEX

Explanations

words related to professions or titles

oai_token-act-pair · gpt-3.5-turbo

terminology related to various roles and positions in organizations or institutions

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

vironment

-0.78

schild

-0.77

ourning

-0.74

lyak

-0.71

imeo

-0.70

hovah

-0.68

ternity

-0.68

uden

-0.66

eas

-0.65

olithic

-0.65

POSITIVE LOGITS

SHIP

0.77

 thereof

0.77

ially

0.76

ship

0.75

itative

0.73

ial

0.71

ãĥĨãĤ£

0.69

 extraord

0.69

itatively

0.68

Factor

0.66

Activations Density 0.117%

words related to professions or titles

terminology related to various roles and positions in organizations or institutions

No Comments

No Known Activations