INDEX

Explanations

text related to dialogues and discussions, particularly with a focus on statements or questions

oai_token-act-pair · gpt-3.5-turbo

phrases or symbols associated with interruptions and pauses in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

orts

-0.69

 womb

-0.65

utterstock

-0.65

 disposal

-0.59

obos

-0.58

ModLoader

-0.58

 accompany

-0.58

 sling

-0.58

bag

-0.58

reens

-0.57

POSITIVE LOGITS

––

1.06

————

1.06

————————

0.95

perhaps

0.92

âĢķ

0.88

âĢ¢âĢ¢

0.87

say

0.87

maybe

0.86

there

0.84

—-

0.83

Activations Density 0.223%

text related to dialogues and discussions, particularly with a focus on statements or questions

phrases or symbols associated with interruptions and pauses in conversation

No Comments

No Known Activations