INDEX

Explanations

references to tasks or assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

'}>

-0.90

 GenerationType

-0.88

μερα

-0.79

 Marac

-0.79

smöglichkeiten

-0.75

︎

-0.74

vea

-0.74

']}

-0.73

biri

-0.73

 infile

-0.71

POSITIVE LOGITS

 tasks

2.53

 task

2.49

 Task

2.33

 Tasks

2.29

Task

2.24

tasks

2.19

 TASK

2.19

Tasks

2.11

TASK

2.10

task

2.10

Activations Density 0.027%

references to tasks or assignments

No Comments

No Known Activations