INDEX

Explanations

phrases expressing acceptance or agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

++++++++++++++++

-0.57

`]

-0.56

complexType

-0.55

͘

-0.54

<%=

-0.54

 Pugh

-0.53

 prove

-0.52

_',

-0.52

."</

-0.51

 Boch

-0.51

POSITIVE LOGITS

 InputDecoration

0.73

שי

0.68

 suffices

0.68

Fine

0.68

Билгалдахарш

0.68

 corriente

0.67

tagHelperRunner

0.67

 okay

0.66

jetbrains

0.65

 Fine

0.64

Activations Density 0.156%

phrases expressing acceptance or agreement

No Comments

No Known Activations

phrases expressing acceptance or agreement

No Comments

No Known Activations