INDEX

Explanations

mentions of or references to supervisors in a professional setting

oai_token-act-pair · gpt-3.5-turbo

references to supervisors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rams

-0.84

ted

-0.78

enburg

-0.77

glers

-0.75

bed

-0.74

aciously

-0.74

ting

-0.70

aji

-0.69

auntlets

-0.69

ilde

-0.68

POSITIVE LOGITS

 supervisor

1.03

 supervisors

0.88

 Supervisor

0.88

 overseeing

0.75

NBC

0.71

 tasked

0.71

Review

0.68

intendent

0.68

IAL

0.68

 Sergeant

0.67

Activations Density 0.011%

mentions of or references to supervisors in a professional setting

references to supervisors in various contexts

No Comments

No Known Activations