INDEX

Explanations

examples or instances of a concept or phenomenon

oai_token-act-pair · gpt-3.5-turbo

instances of the word "example" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

scribe

-0.74

quer

-0.71

quire

-0.71

awa

-0.69

ties

-0.67

zos

-0.67

ternity

-0.66

 livest

-0.66

tones

-0.64

 neighb

-0.63

POSITIVE LOGITS

 illustrating

1.01

of

0.96

 thereof

0.94

why

0.93

 examples

0.86

 exempl

0.80

Examples

0.78

Of

0.78

 demonstrating

0.74

how

0.73

Activations Density 0.046%

examples or instances of a concept or phenomenon

instances of the word "example" in various contexts

No Comments

No Known Activations