INDEX

Explanations

numerical codes and statuses likely related to a specific system or process

oai_token-act-pair · gpt-3.5-turbo

numerical data and status updates

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

 nomine

-0.89

ortunately

-0.78

 exha

-0.69

Orderable

-0.66

 princ

-0.66

 neighb

-0.66

 councill

-0.65

 citiz

-0.65

 smartest

-0.65

 newsp

-0.63

POSITIVE LOGITS

1.55

1.53

1.52

1.51

1.50

Activations Density 0.045%

numerical codes and statuses likely related to a specific system or process

numerical data and status updates

No Comments

No Known Activations