INDEX

Explanations

expressions related to close physical proximity and confrontation

oai_token-act-pair · gpt-3.5-turbo

terms related to physical proximity and confrontation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ection

-0.69

itÃ©

-0.68

IENCE

-0.65

igation

-0.64

ngth

-0.64

eg

-0.63

MENT

-0.63

MQ

-0.61

gments

-0.61

vg

-0.60

POSITIVE LOGITS

 wise

0.83

wise

0.81

lessly

0.80

ishly

0.76

ously

0.74

by

0.74

ily

0.74

ways

0.71

wide

0.71

arily

0.69

Activations Density 0.157%

expressions related to close physical proximity and confrontation

terms related to physical proximity and confrontation

No Comments

No Known Activations