INDEX

Explanations

expressions of approximation or near-certainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lugs

-0.72

 Guen

-0.66

bufio

-0.65

 Magdeburg

-0.64

 piele

-0.62

 culoare

-0.62

GenerationType

-0.61

 flamengo

-0.61

ṇ

-0.60

seamnă

-0.60

POSITIVE LOGITS

 nearly

1.23

 almost

1.14

Casi

1.09

 Almost

1.07

Almost

1.05

 Nearly

1.04

nearly

1.02

 Casi

1.01

>\<^

0.97

Nearly

0.97

Activations Density 0.078%

expressions of approximation or near-certainty

No Comments

No Known Activations