INDEX

Explanations

terms related to specific medical conditions or medical technology

oai_token-act-pair · gpt-3.5-turbo

end-of-text markers or document delimiters

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

sburgh

-0.80

itudes

-0.77

 undet

-0.67

 actionGroup

-0.66

ulators

-0.65

ãģĻ

-0.65

ONSORED

-0.64

andise

-0.64

ships

-0.61

ambo

-0.61

POSITIVE LOGITS

hyde

0.92

ynam

0.85

ynamic

0.85

cember

0.84

etermin

0.81

ependent

0.80

NF

0.79

Mub

0.78

RECT

0.76

etermination

0.75

Activations Density 0.202%

terms related to specific medical conditions or medical technology

end-of-text markers or document delimiters

No Comments

No Known Activations