INDEX

Explanations

instances where some action or support is withdrawn or cancelled

oai_token-act-pair · gpt-3.5-turbo

instances of support or withdrawal of support 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

»Ĵ

-0.73

stals

-0.72

elli

-0.71

uzzle

-0.67

ogenous

-0.67

agog

-0.66

rill

-0.66

agogue

-0.65

rices

-0.65

strate

-0.65

POSITIVE LOGITS

 scheduled

0.99

 planned

0.97

 pending

0.96

 altogether

0.93

 participation

0.92

 registrations

0.90

 indefinitely

0.88

 plans

0.86

 invitations

0.86

 entire

0.85

Activations Density 0.254%

instances where some action or support is withdrawn or cancelled

instances of support or withdrawal of support in various contexts

No Comments

No Known Activations