INDEX

Explanations

phrases that involve a realization or understanding of something

oai_token-act-pair · gpt-3.5-turbo

instances of realization or understanding

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

inion

-0.86

ific

-0.71

itives

-0.70

 Mandatory

-0.64

uti

-0.64

 Hancock

-0.64

ometers

-0.64

ths

-0.63

oway

-0.63

idon

-0.63

POSITIVE LOGITS

ODY

0.71

 mistakes

0.66

 hesitation

0.66

atorium

0.65

 mistake

0.65

 anew

0.65

[_

0.65

 passion

0.64

 similarities

0.63

 pandemonium

0.61

Activations Density 0.225%

phrases that involve a realization or understanding of something

instances of realization or understanding

No Comments

No Known Activations