INDEX

Explanations

phrases relating to self-referential expressions and personal pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.51

 khoan

-0.41

’

-0.40

 quoi

-0.39

 annen

-0.39

 identification

-0.39

TagHelpers

-0.38

 köy

-0.38

 vaikka

-0.38

 place

-0.38

POSITIVE LOGITS

AutoScaleMode

0.99

 كومونز

0.97

 myself

0.90

 myſelf

0.88

myself

0.87

 Myself

0.84

BufferException

0.83

исленность

0.81

complexContent

0.81

Numerology

0.80

Activations Density 0.186%

phrases relating to self-referential expressions and personal pronouns

No Comments

No Known Activations