INDEX

Explanations

names or terms related to "Rat" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Rat" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

PLIED

-0.80

 EDITION

-0.70

Ļ½

-0.69

©¶æ

-0.68

¬¼

-0.67

 Catalonia

-0.66

«ĺ

-0.65

OURCE

-0.64

Reloaded

-0.63

âĢ¢âĢ¢

-0.63

POSITIVE LOGITS

chet

1.55

che

0.94

cliffe

0.93

imilation

0.92

rollers

0.91

ting

0.89

ename

0.87

rice

0.86

Rat

0.86

emy

0.86

Activations Density 0.007%

names or terms related to "Rat" followed by a numerical value

occurrences of the term "Rat" in various contexts

No Comments

No Known Activations