INDEX

Explanations

phrases related to executive and officer positions in organizations

oai_token-act-pair · gpt-3.5-turbo

job titles related to high-level corporate positions

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

ewitness

-0.82

otom

-0.71

leys

-0.69

Military

-0.69

haps

-0.69

 Gladiator

-0.68

paren

-0.66

cend

-0.64

 convict

-0.63

ramid

-0.63

POSITIVE LOGITS

ABV

0.77

 emer

0.74

âĢ¢âĢ¢

0.73

)=(

0.71

 thereof

0.70

oft

0.68

 Stacy

0.68

 Steph

0.68

Initialized

0.68

 Saur

0.67

Activations Density 0.091%

phrases related to executive and officer positions in organizations

job titles related to high-level corporate positions

No Comments

No Known Activations