INDEX

Explanations

words related to positions or roles within organizations

oai_token-act-pair · gpt-3.5-turbo

phrases referencing organizational boards or governing bodies

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

ashtra

-1.04

hematically

-0.71

aan

-0.70

vell

-0.70

ãĤ¼ãĤ¦ãĤ¹

-0.64

 strain

-0.62

ãĤ®

-0.62

 Ãľ

-0.62

 tears

-0.61

 tremend

-0.61

POSITIVE LOGITS

 Directors

1.03

 Governors

0.92

 directors

0.87

 trustees

0.78

interstitial

0.78

 Inquiry

0.74

 governors

0.73

arters

0.70

orts

0.69

ature

0.69

Activations Density 0.052%

words related to positions or roles within organizations

phrases referencing organizational boards or governing bodies

No Comments

No Known Activations