INDEX

Explanations

instances of comparative language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

NegativeButton

-0.75

 Henn

-0.68

 Rosenberg

-0.64

Man

-0.63

entu

-0.61

entgen

-0.60

ffman

-0.58

sphase

-0.57

 Fielding

-0.56

Bism

-0.56

POSITIVE LOGITS

 Comparisons

1.54

 comparison

1.51

 comparisons

1.50

 Comparing

1.42

 compares

1.40

 Comparison

1.40

 compar

1.36

 compared

1.36

 Compare

1.34

 comparing

1.34

Activations Density 0.144%

instances of comparative language

No Comments

No Known Activations