INDEX

Explanations

abbreviations for states in the United States

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically the period

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

imates

-0.78

orical

-0.78

INAL

-0.76

itia

-0.70

oric

-0.68

ogen

-0.65

alyses

-0.62

ocrates

-0.61

okin

-0.61

idious

-0.61

POSITIVE LOGITS

etc

0.81

 citing

0.75

 Boone

0.72

etc

0.72

...]

0.69

Jr

0.67

 EntityItem

0.66

ooters

0.66

ynski

0.66

CLASSIFIED

0.66

Activations Density 0.030%

abbreviations for states in the United States

punctuation marks, specifically the period

No Comments

No Known Activations