INDEX

Explanations

phrases and words related to the term "OpenMind"

oai_token-act-pair · gpt-3.5-turbo

references to an open-source or open-access context

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

_-

-0.80

akuya

-0.74

 Kear

-0.73

kh

-0.71

upper

-0.69

ashtra

-0.68

jad

-0.66

ãĤ©

-0.65

nir

-0.65

agher

-0.65

POSITIVE LOGITS

edo

0.74

ternity

0.72

 harbor

0.70

 doors

0.65

 Pandora

0.64

ended

0.64

 backdoor

0.64

 portal

0.62

 sandbox

0.62

 dialog

0.62

Activations Density 0.095%

phrases and words related to the term "OpenMind"

references to an open-source or open-access context

No Comments

No Known Activations