INDEX

Explanations

references to pain and discomfort

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

μως

-0.86

theless

-0.84

camore

-0.81

ssohn

-0.79

 himo

-0.77

lotl

-0.76

dehyde

-0.75

 Vergara

-0.75

Према

-0.74

 propOrder

-0.73

POSITIVE LOGITS

 pain

2.43

 Pain

2.29

Pain

2.19

pain

2.17

 PAIN

2.10

 pains

1.83

 douleur

1.47

 dolor

1.47

 painful

1.42

 Schmerz

1.29

Activations Density 0.084%

references to pain and discomfort

No Comments

No Known Activations