INDEX

Explanations

statements of opinion or declaration

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

 Staub

-0.82

']")

-0.77

`]

-0.74

</table>

-0.69

FLO

-0.67

.-.

-0.67

'>";

-0.66

 Thornton

-0.66

Gera

-0.66

POL

-0.65

POSITIVE LOGITS

SAY

1.64

SAY

1.61

 Says

1.57

 says

1.55

Say

1.52

say

1.52

 Saying

1.51

Say

1.49

say

1.47

Says

1.46

Activations Density 0.099%

statements of opinion or declaration

No Comments

No Known Activations