INDEX

Explanations

words related to dependencies or interdependencies

oai_token-act-pair · gpt-3.5-turbo

terms related to dependence and dependency relationships

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

\\\\\\\\

-0.70

²¾

-0.68

éŃĶ

-0.67

izer

-0.65

quer

-0.65

Marsh

-0.64

izers

-0.64

ventory

-0.63

ning

-0.63

±

-0.62

POSITIVE LOGITS

encies

1.16

 upon

1.04

ency

0.97

 orig

0.91

ently

0.76

 Upon

0.76

ents

0.74

 liability

0.72

rants

0.72

worthiness

0.72

Activations Density 0.048%

words related to dependencies or interdependencies

terms related to dependence and dependency relationships

No Comments

No Known Activations