INDEX

Explanations

technical terms or phrases related to instructions or processes

oai_token-act-pair · gpt-3.5-turbo

statements about procedures and actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Ire

-0.57

VERTISEMENT

-0.56

tips

-0.52

aban

-0.51

]).

-0.50

STAR

-0.49

anooga

-0.49

"],"

-0.48

umni

-0.48

EMS

-0.47

POSITIVE LOGITS

 passively

0.50

 finite

0.48

 physicists

0.46

 oneself

0.46

 perceptual

0.46

 explicitly

0.46

 artificially

0.45

 Slate

0.44

 electrons

0.44

 explicit

0.44

Activations Density 2.454%

technical terms or phrases related to instructions or processes

statements about procedures and actions

No Comments

No Known Activations