INDEX

Explanations

code-related constructs and expressions involving functions and objects

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

-0.59

AsUp

-0.54

-0.53

the

-0.51

 even

-0.50

us

-0.49

it

-0.48

and

-0.48

POSITIVE LOGITS

 pleaſure

1.01

 ſtand

0.99

 purpoſe

0.95

 ſtate

0.95

 cauſe

0.95

 ſche

0.94

 uſe

0.93

mybatisplus

0.92

 reaſon

0.92

uſ

0.91

Activations Density 0.380%

code-related constructs and expressions involving functions and objects

No Comments

No Known Activations