INDEX

Explanations

information related to encounters or discoveries

oai_token-act-pair · gpt-3.5-turbo

instances of discovering, finding, or coming across something during an experience or journey

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

includes

-0.74

olute

-0.72

igure

-0.69

 ensures

-0.67

 reliant

-0.67

stroke

-0.66

 accountable

-0.66

 subord

-0.65

integ

-0.64

except

-0.64

POSITIVE LOGITS

 browsing

0.80

 Travels

0.77

 accident

0.77

 stumbled

0.72

amazon

0.70

chance

0.70

 researching

0.70

ibrary

0.69

 chemist

0.69

 classmate

0.69

Activations Density 0.516%

information related to encounters or discoveries

instances of discovering, finding, or coming across something during an experience or journey

No Comments

No Known Activations