INDEX

Explanations

actions related to reading or browsing through content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ArrowToggle

-0.56

modelBuilder

-0.53

linearGradient

-0.47

InputTagHelper

-0.46

ItemBackground

-0.45

OData

-0.45

ragan

-0.44

Ket

-0.44

SBATCH

-0.44

makeConstraints

-0.43

POSITIVE LOGITS

 flipping

1.12

 flipped

0.99

 flip

0.97

 flips

0.88

Flip

0.86

flip

0.85

Fli

0.85

 Flip

0.82

Fli

0.81

flipped

0.78

Activations Density 0.417%

actions related to reading or browsing through content

No Comments

No Known Activations

actions related to reading or browsing through content

No Comments

No Known Activations