INDEX

Explanations

the word "Variable" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to variables in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ifice

-0.78

AME

-0.77

letters

-0.76

HCR

-0.76

Opening

-0.75

ä½ľ

-0.75

Phones

-0.73

âĹ¼

-0.72

lyak

-0.71

furt

-0.71

POSITIVE LOGITS

 variable

1.07

 variables

0.90

 Variable

0.90

etheless

0.81

variable

0.80

 capacitor

0.76

 flares

0.74

 belts

0.72

 streaks

0.71

 resistor

0.71

Activations Density 0.007%

the word "Variable" in various contexts

references to variables in programming contexts

No Comments

No Known Activations