INDEX

Explanations

terms related to peer review and peer interactions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

äksi

-0.69

 propOrder

-0.67

 uParam

-0.65

ļ

-0.61

ActionCreators

-0.59

 ostavi

-0.59

cellaneous

-0.59

horabuena

-0.58

ToBounds

-0.57

POSITIVE LOGITS

 peer

3.61

 Peer

3.32

Peer

3.17

peer

3.09

 peers

2.87

 Peers

2.58

peers

2.42

PEER

2.40

Peers

2.24

 peered

1.24

Activations Density 0.071%

terms related to peer review and peer interactions

No Comments

No Known Activations