INDEX

Explanations

mentions of the name "Biden", particularly focusing on those with higher activation values

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Biden."

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

Ö¼

-0.79

 ILCS

-0.78

Reviewer

-0.77

ivities

-0.73

ãĤ®

-0.71

ortmund

-0.70

ateur

-0.68

ELF

-0.68

orically

-0.68

ivated

-0.67

POSITIVE LOGITS

 Biden

1.26

zag

0.85

 Caucus

0.80

mire

0.80

jug

0.75

 appoint

0.71

 aide

0.71

 nominated

0.69

 Bros

0.69

Jr

0.68

Activations Density 0.014%

mentions of the name "Biden", particularly focusing on those with higher activation values

mentions of the name "Biden."

No Comments

No Known Activations