INDEX

Explanations

references to quotes and reported speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 titled

-0.56

 named

-0.55

 called

-0.54

 denominada

-0.53

 termed

-0.52

UrlResolution

-0.51

 denominado

-0.50

called

-0.50

cemment

-0.49

 nicknamed

-0.48

POSITIVE LOGITS

InputBorder

0.61

AddTagHelper

0.60

 BoxFit

0.57

 InputDecoration

0.56

 everytime

0.56

 ovunque

0.55

BagConstraints

0.55

ArgsConstructor

0.53

 followed

0.52

 repeatedly

0.51

Activations Density 0.287%

references to quotes and reported speech

No Comments

No Known Activations