INDEX

Explanations

terms related to data structures and tasks within a programming or scripting context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Билгалдахарш

-0.62

 '\\;'

-0.57

 trial

-0.52

ponenten

-0.47

<eos>

-0.47

EDEFAULT

-0.46

LabelTagHelper

-0.46

'])->

-0.45

++);

-0.45

 CYTHON

-0.45

POSITIVE LOGITS

listdir

0.62

 shur

0.57

lijst

0.56

CrossRef

0.55

DoubleQuotes

0.55

ARU

0.54

 Skyl

0.54

ORUM

0.53

 Perfon

0.52

 Diſ

0.52

Activations Density 0.571%

terms related to data structures and tasks within a programming or scripting context

No Comments

No Known Activations

terms related to data structures and tasks within a programming or scripting context

No Comments

No Known Activations