INDEX

Explanations

phrases related to communication and interaction

oai_token-act-pair · gpt-3.5-turbo

references to emotive expressions or personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 tremend

-0.72

anwhile

-0.72

odka

-0.68

©¶æ

-0.67

 minim

-0.66

 decomp

-0.65

enta

-0.64

ussian

-0.63

nown

-0.63

 eject

-0.63

POSITIVE LOGITS

âĹ¼

0.79

ONSORED

0.79

said

0.77

Â¯

0.77

âĢķ

0.76

ðŁĺ

0.72

ISIS

0.72

âĸº

0.72

 Rapids

0.70

orne

0.70

Activations Density 0.519%

phrases related to communication and interaction

references to emotive expressions or personal experiences

No Comments

No Known Activations