INDEX

Explanations

mentions of exposure to various conditions or events

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

httphttps

-0.83

 Granger

-0.77

('/:

-0.70

 rimb

-0.69

chränk

-0.68

iverr

-0.67

(!__

-0.66

GridData

-0.66

RTRS

-0.65

 Herring

-0.65

POSITIVE LOGITS

 exposure

2.51

 Exposure

2.31

exposure

2.26

Exposure

2.15

 exposures

2.15

 exposed

2.13

 expose

2.06

 exposing

2.06

 EXPOSURE

2.05

Exposed

2.03

Activations Density 0.140%

mentions of exposure to various conditions or events

No Comments

No Known Activations