INDEX

Explanations

words related to unity, resistance, and empowerment

oai_token-act-pair · gpt-3.5-turbo

themes related to struggle, resilience, and collective action for a cause

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 occasional

-0.81

 disliked

-0.81

 annoyance

-0.80

similar

-0.79

 normally

-0.76

 frowned

-0.74

 dislike

-0.73

 complains

-0.73

 annoying

-0.73

 occasionally

-0.73

POSITIVE LOGITS

Together

1.03

ISSION

0.90

çīĪ

0.85

ãĢ

0.85

Ready

0.85

à¼

0.84

âľ

0.84

âĢ

0.84

âĦ¢:

0.83

 Blueprint

0.83

Activations Density 0.917%

words related to unity, resistance, and empowerment

themes related to struggle, resilience, and collective action for a cause

No Comments

No Known Activations