INDEX

Explanations

references to medical treatment or care within a legal or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GeoNames

-0.59

исленность

-0.58

OUNTS

-0.57

orong

-0.57

 "");

-0.56

Eres

-0.56

}{*}{

-0.55

 kres

-0.54

rrbracket

-0.54

 Schilling

-0.53

POSITIVE LOGITS

0.89

 EconPapers

0.89

 ✭✭

0.89

 Llew

0.81

 paroisse

0.73

CloseHandle

0.72

DockStyle

0.72

</thead>

0.71

 Ashe

0.70

 giù

0.69

Activations Density 0.093%

references to medical treatment or care within a legal or formal context

No Comments

No Known Activations