INDEX

Explanations

requests for assistance or support from the audience

oai_token-act-pair · gpt-3.5-turbo

calls for assistance or support from the audience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pheus

-0.81

yang

-0.73

Hung

-0.72

erg

-0.70

AMS

-0.68

ãĤ£

-0.68

prus

-0.67

porting

-0.67

vae

-0.66

wolves

-0.65

POSITIVE LOGITS

 Majesty

0.74

 asses

0.74

 Javascript

0.73

iest

0.71

 pawn

0.71

 mate

0.70

 dear

0.69

 selves

0.69

 Favorite

0.66

 preference

0.66

Activations Density 0.200%

requests for assistance or support from the audience

calls for assistance or support from the audience

No Comments

No Known Activations