INDEX

Explanations

lessons or moral insights

oai_token-act-pair · gpt-3.5-turbo

references to lessons or teachings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AE

-0.64

å¯

-0.61

 Origins

-0.59

 Keep

-0.59

[|

-0.58

Ds

-0.58

 Unlock

-0.57

 Dresden

-0.57

 Freeze

-0.57

âĹ¼

-0.56

POSITIVE LOGITS

 than

1.15

ened

1.12

ening

1.04

 fortunate

1.00

ons

0.96

ens

0.90

 travelled

0.87

 traveled

0.85

than

0.82

ener

0.79

Activations Density 0.056%

lessons or moral insights

references to lessons or teachings

No Comments

No Known Activations