INDEX

Explanations

conversations dissecting the meanings or implications of statements and events

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

endphp

-0.53

ftagPool

-0.51

いかがでしょうか

-0.49

fromnode

-0.47

ábbi

-0.45

PerformLayout

-0.44

devamını

-0.42

chaften

-0.41

いかが

-0.41

Izvori

-0.41

POSITIVE LOGITS

 means

3.44

means

3.10

 mean

3.00

 meaning

2.99

 Means

2.96

 MEANS

2.86

Means

2.84

 MEAN

2.72

meaning

2.55

Meaning

2.54

Activations Density 0.778%

conversations dissecting the meanings or implications of statements and events

No Comments

No Known Activations