INDEX

Explanations

references to experiments and experimental setups

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

experiments conducted

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AddTagHelper

-0.46

#+#

-0.45

 būs

-0.43

 springfox

-0.39

 sanguí

-0.38

yscy

-0.38

tidaknya

-0.36

gnition

-0.35

WebpackPlugin

-0.35

 nakalista

-0.35

POSITIVE LOGITS

 experiments

0.90

experiments

0.83

 experiment

0.82

 experimento

0.74

experiment

0.73

 Experiments

0.73

 experim

0.72

 Experiment

0.69

Experiments

0.69

 EXPERIMENTS

0.68

Activations Density 0.156%

references to experiments and experimental setups

experiments conducted

No Comments

No Known Activations