INDEX

Explanations

references to data size and memory specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 MainAxisSize

-0.63

Portale

-0.56

thenReturn

-0.55

UnusedPrivate

-0.50

Amir

-0.49

 Amir

-0.49

 onAnimation

-0.49

 brasil

-0.48

 provinciale

-0.48

Sucesor

-0.47

POSITIVE LOGITS

MB

1.33

MB

1.31

meg

1.17

 bytes

1.16

KB

1.11

Meg

1.10

 byte

1.07

KB

1.05

Mb

1.05

 Bytes

1.03

Activations Density 0.562%

references to data size and memory specifications

No Comments

No Known Activations