INDEX

Explanations

phrases indicating alternative options or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

expandindo

-0.93

dymyr

-0.87

#+#

-0.80

mPaint

-0.73

dasarkan

-0.72

arithmic

-0.71

kadot

-0.71

 télévis

-0.70

 sientes

-0.70

 vostri

-0.69

POSITIVE LOGITS

 Alternative

1.65

Alternative

1.65

 alternatives

1.64

 alternative

1.63

 Alternatives

1.54

Alternatives

1.50

 ALTERNATIVE

1.42

 ALTERN

1.36

 altern

1.34

alternative

1.33

Activations Density 0.079%

phrases indicating alternative options or approaches

No Comments

No Known Activations