INDEX

Explanations

non-specific terms or phrases related to various topics

oai_token-act-pair · gpt-3.5-turbo

terms related to versions and states of being or existing

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udeau

-0.67

ipeg

-0.67

incial

-0.65

aukee

-0.65

terday

-0.64

 pause

-0.63

arb

-0.59

ãĥķãĤ©

-0.59

------

-0.58

ãĥĥãĥī

-0.58

POSITIVE LOGITS

 nearest

0.88

 closest

0.82

 chosen

0.70

 furthe

0.69

adobe

0.68

 mentioned

0.67

 studied

0.67

same

0.67

hest

0.67

 listed

0.66

Activations Density 0.562%

non-specific terms or phrases related to various topics

terms related to versions and states of being or existing

No Comments

No Known Activations