INDEX

Explanations

programming-related syntax or code elements

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

 tartalomajánló

-0.98

 ProtoMessage

-0.92

BeginContext

-0.90

extAlignment

-0.89

ItemBackground

-0.88

 /\.(

-0.87

 nahilalakip

-0.87

 Roskov

-0.86

 lenker

-0.85

NUMX

-0.85

POSITIVE LOGITS

0.50

</em>

0.48

sig

0.47

who

0.47

stdc

0.45

isiaj

0.45

0.44

forward

0.43

is

0.43

Activations Density 0.153%

programming-related syntax or code elements

No Comments

No Known Activations