INDEX

Explanations

terms related to medical and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

RenderAtEndOf

-0.68

metries

-0.66

dighet

-0.65

锈钢

-0.64

parency

-0.64

GEBURTSDATUM

-0.64

uisine

-0.61

ressee

-0.60

lorette

-0.60

urlpatterns

-0.59

POSITIVE LOGITS

 enough

1.54

enough

1.06

 genug

1.04

 demais

1.00

 genoeg

1.00

 ENOUGH

0.97

 Enough

0.88

Enough

0.86

yet

0.78

 compared

0.77

Activations Density 0.817%

terms related to medical and scientific concepts

No Comments

No Known Activations