INDEX

Explanations

percentages and numerical values related to changes over time

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" followed by various numerical indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

went

-0.68

oris

-0.67

sbm

-0.67

reprene

-0.67

sle

-0.65

lance

-0.65

isco

-0.64

urred

-0.63

icipated

-0.61

grain

-0.60

POSITIVE LOGITS

 stabilize

0.88

 save

0.82

 compensate

0.78

ilet

0.76

 conserve

0.76

 accommodate

0.75

pless

0.74

ggles

0.73

éĹĺ

0.73

 include

0.71

Activations Density 0.157%

percentages and numerical values related to changes over time

instances of the word "to" followed by various numerical indicators

No Comments

No Known Activations