INDEX

Explanations

references to legal terminology and court processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

<bos>

-1.19

-0.69

-0.62

The

-0.61

can

-0.61

in

-0.59

on

-0.59

</td>

-0.59

-0.58

POSITIVE LOGITS

 дописавши

0.94

 jsPsych

0.92

########.

0.91

 bezeichneter

0.85

PerformLayout

0.84

 OMITBAD

0.83

 doubtnut

0.83

 auffi

0.82

 ―――――

0.81

 herbic

0.80

Activations Density 1.073%

references to legal terminology and court processes

No Comments

No Known Activations