INDEX

Explanations

information related to structured data queries and programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 television

-0.53

 government

-0.51

 televisão

-0.47

 dumne

-0.46

AAAAAAAAAAAAAAAA

-0.46

 technological

-0.46

 halaman

-0.45

 beziehungs

-0.45

 maximum

-0.45

 character

-0.44

POSITIVE LOGITS

aarrggbb

0.99

 Engr

0.89

oredCriteria

0.86

 Univ

0.86

yrs

0.84

enderror

0.84

 choc

0.83

ereq

0.82

Univ

0.82

msgTypes

0.81

Activations Density 2.814%

information related to structured data queries and programming code

No Comments

No Known Activations

information related to structured data queries and programming code

No Comments

No Known Activations