INDEX

Explanations

statements of identity and self-description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

RenderAtEndOf

-0.76

 Pliny

-0.76

 transfieras

-0.72

 wanna

-0.71

 NDEBUG

-0.70

 Allegretto

-0.70

ViewFeatures

-0.70

сихо

-0.70

multicolumn

-0.69

 GONNA

-0.69

POSITIVE LOGITS

mektedir

0.92

 paesi

0.79

 geführt

0.75

miştir

0.74

melidir

0.74

lisi

0.73

mıştır

0.72

 goederen

0.68

 angekommen

0.67

ayon

0.67

Activations Density 0.396%

statements of identity and self-description

No Comments

No Known Activations