INDEX

Explanations

reflexive pronouns and expressions of self-reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Desta

-0.56

\}\\

-0.56

NonQuery

-0.55

 tonic

-0.54

 enrique

-0.54

asilan

-0.54

jkl

-0.53

manas

-0.53

 panoramique

-0.52

 Ergänzung

-0.52

POSITIVE LOGITS

itself

1.71

 itself

1.67

 Itself

1.50

themselves

1.23

 themselves

1.16

 himself

1.12

 Himself

1.09

 сама

1.08

 zelf

1.07

 selve

1.03

Activations Density 0.076%

reflexive pronouns and expressions of self-reference

No Comments

No Known Activations