INDEX

Explanations

phrases related to hierarchical levels or positions

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to rank and hierarchy within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

argo

-0.79

agic

-0.71

 Anita

-0.68

\/\/

-0.67

ogle

-0.66

orescence

-0.66

issance

-0.66

reens

-0.65

credit

-0.64

vous

-0.63

POSITIVE LOGITS

 insign

1.03

quo

0.88

loader

0.81

naire

0.81

nance

0.80

enance

0.77

leading

0.76

Rank

0.76

 ranks

0.75

ings

0.74

Activations Density 0.036%

phrases related to hierarchical levels or positions

terms and phrases related to rank and hierarchy within organizations

No Comments

No Known Activations