INDEX

Explanations

phrases indicating the presence of specific individuals in different settings

oai_token-act-pair · gpt-3.5-turbo

references to group dynamics or hierarchical structures 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 @ 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

uristic

-0.68

Topics

-0.68

ILA

-0.65

brate

-0.63

iu

-0.61

lessness

-0.60

sever

-0.59

 Extensions

-0.58

Phys

-0.58

ometers

-0.57

POSITIVE LOGITS

 midst

1.21

 room

1.15

 closet

1.08

 foreground

1.05

 doorway

1.03

 vicinity

0.99

 fray

0.98

 trenches

0.97

 womb

0.96

 picture

0.94

Activations Density 0.218%

phrases indicating the presence of specific individuals in different settings

references to group dynamics or hierarchical structures in various contexts

No Comments

No Known Activations