INDEX

Explanations

mentions of physical objects

oai_token-act-pair · gpt-3.5-turbo

references to physical or conceptual "units" 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 @ 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

 Marketable

-0.76

aukee

-0.72

NetMessage

-0.71

vous

-0.67

 straw

-0.66

å¦

-0.65

é»Ĵ

-0.65

 Earthqu

-0.65

gian

-0.64

etsk

-0.64

POSITIVE LOGITS

mates

1.02

mate

1.00

 unit

0.95

 units

0.94

unit

0.92

units

0.90

imet

0.88

Unit

0.87

arily

0.86

matically

0.84

Activations Density 0.011%

mentions of physical objects

references to physical or conceptual "units" in various contexts

No Comments

No Known Activations