INDEX

Explanations

the word "such" followed by a descriptive phrase or noun

oai_token-act-pair · gpt-3.5-turbo

the word "such" and its variations to highlight specific contexts or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ertodd

-0.80

oil

-0.76

 Loaded

-0.74

wives

-0.73

 Murd

-0.73

achus

-0.72

ocene

-0.71

kick

-0.70

ipedia

-0.69

ysc

-0.69

POSITIVE LOGITS

ties

0.89

 matters

0.71

ities

0.69

 kinds

0.69

 amounts

0.66

aug

0.66

 consequential

0.66

 heinous

0.64

 stringent

0.64

 sorts

0.64

Activations Density 0.049%

the word "such" followed by a descriptive phrase or noun

the word "such" and its variations to highlight specific contexts or references

No Comments

No Known Activations