INDEX

Explanations

references to different tiers, such as Tier 7, Tier 8, and Tier 9

oai_token-act-pair · gpt-3.5-turbo

references to hierarchical classifications or levels, particularly regarding tiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

okia

-0.86

issance

-0.81

mercial

-0.71

hur

-0.70

 Liberties

-0.61

sky

-0.61

ãĥĻ

-0.60

 Evening

-0.59

natureconservancy

-0.58

 Predators

-0.58

POSITIVE LOGITS

 tiers

0.86

 tier

0.82

uple

0.80

 guiActiveUnfocused

0.74

arity

0.74

ney

0.73

neys

0.72

Tier

0.68

 bracket

0.67

anza

0.65

Activations Density 0.026%

references to different tiers, such as Tier 7, Tier 8, and Tier 9

references to hierarchical classifications or levels, particularly regarding tiers

No Comments

No Known Activations