INDEX

Explanations

references to spatial relationships involving the subject 'him' or 'them'

oai_token-act-pair · gpt-3.5-turbo

references to individuals and groups in relation to positions or actions

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

ãĥ©ãĥ³

-0.80

 Geek

-0.70

-)

-0.69

fact

-0.69

ãĥĭ

-0.66

inctions

-0.65

ammy

-0.65

Psy

-0.64

ociate

-0.62

itialized

-0.61

POSITIVE LOGITS

atic

0.83

 conduc

0.82

atics

0.81

 selves

0.77

alian

0.76

 tremend

0.69

 dracon

0.69

 unbeat

0.68

 contemporaries

0.67

andering

0.66

Activations Density 0.177%

references to spatial relationships involving the subject 'him' or 'them'

references to individuals and groups in relation to positions or actions

No Comments

No Known Activations