INDEX

Explanations

specific acronyms related to organizations or programs, especially those denoted by 'OP'

oai_token-act-pair · gpt-3.5-turbo

mentions of organizations or committees, particularly those related to environmental or political topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥīãĥ©ãĤ´ãĥ³

-0.96

 Monstrous

-0.73

 Aval

-0.72

 Carib

-0.70

ãĥĨãĤ£

-0.70

 Bermuda

-0.67

 Cantor

-0.67

ãģ®å®

-0.66

 à¨

-0.65

ãĥĸ

-0.65

POSITIVE LOGITS

olicy

1.20

yright

1.13

etition

1.11

arent

1.10

rompt

1.10

inion

1.09

OP

1.08

ropri

1.08

lyak

1.07

rint

1.06

Activations Density 0.007%

specific acronyms related to organizations or programs, especially those denoted by 'OP'

mentions of organizations or committees, particularly those related to environmental or political topics

No Comments

No Known Activations