INDEX

Explanations

numeric information, such as counts or rankings

oai_token-act-pair · gpt-3.5-turbo

numerical data and counts related to entities or groups 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

matter

-0.77

icz

-0.75

WAR

-0.74

ptroller

-0.73

charge

-0.71

aeus

-0.70

Shift

-0.70

ivot

-0.69

cycle

-0.68

oÄŁ

-0.67

POSITIVE LOGITS

 finalists

1.21

 remaining

0.98

 contenders

0.85

 surviving

0.83

 quir

0.81

 qualifying

0.81

 possible

0.81

 applicants

0.81

 claimants

0.80

 eligible

0.80

Activations Density 0.092%

numeric information, such as counts or rankings

numerical data and counts related to entities or groups in various contexts

No Comments

No Known Activations