INDEX

Explanations

phrases related to actions or interactions

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "the" and its function 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

unin

-0.75

Indian

-0.73

Bal

-0.72

hemy

-0.68

oin

-0.67

Ã°

-0.67

thood

-0.67

 Maced

-0.65

Ã¨re

-0.64

nir

-0.63

POSITIVE LOGITS

stretched

0.79

 wrinkles

0.73

 basics

0.71

 flyers

0.69

OSP

0.66

 baseline

0.66

 frustrations

0.66

println

0.61

 reluct

0.61

 laundry

0.61

Activations Density 0.269%

phrases related to actions or interactions

the presence of the word "the" and its function in various contexts

No Comments

No Known Activations