INDEX

Explanations

references to soap and related terminology

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

BuildContext

-0.64

GLuint

-0.54

par

-0.52

(&:

-0.49

simo

-0.49

 mAdapter

-0.47

 sola

-0.47

ý

-0.46

Er

-0.46

Par

-0.46

POSITIVE LOGITS

 CreateTagHelper

1.96

AddTagHelper

1.53

ftagPool

1.34

 ProtoMessage

1.13

 ModelExpression

1.07

jupiter

1.05

 propOrder

1.03

SequentialGroup

0.99

soap

0.98

TagHelpers

0.96

Activations Density 0.006%

references to soap and related terminology

No Comments

No Known Activations