INDEX

Explanations

the specific boolean value "false"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Hecht

-0.84

EndContext

-0.84

زیین

-0.81

 referenties

-0.80

 وتسجيلات

-0.79

+#+#

-0.78

akesh

-0.75

ductory

-0.72

ンダント

-0.72

 Puig

-0.72

POSITIVE LOGITS

 false

0.90

false

0.82

GraphicsUnit

0.79

 False

0.79

ation

0.77

False

0.76

 fals

0.75

 falsehood

0.73

FALSE

0.72

[]:

0.71

Activations Density 0.072%

the specific boolean value "false"

No Comments

No Known Activations