INDEX

Explanations

names of people and associated references in a narrative context

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

aarrggbb

-0.98

rungsseite

-0.90

AddHtmlAttribute

-0.90

IndentedString

-0.87

TagMode

-0.86

 AssemblyCulture

-0.85

 noDo

-0.85

 समीक्षक

-0.85

@"/

-0.84

featureID

-0.81

POSITIVE LOGITS

 respectively

0.61

 그리고

0.54

 were

0.53

 alike

0.52

are

0.48

 together

0.46

+#+

0.45

一起来

0.44

共

0.43

selves

0.42

Activations Density 0.380%

names of people and associated references in a narrative context

No Comments

No Known Activations