INDEX

Explanations

terms related to counterfactual reasoning and its applications

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

"counter"

np_acts-logits-general · gemini-2.0-flash

words starting with counter

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 fédé

-0.72

 coûts

-0.63

HasColumnName

-0.61

expandindo

-0.59

ostí

-0.58

 متعلقه

-0.58

NgModule

-0.58

 placés

-0.57

cogni

-0.57

 parlato

-0.57

POSITIVE LOGITS

 counter

1.46

 Counter

1.39

 COUNTER

1.38

 counters

1.28

Counter

1.21

counter

1.20

 Counters

1.18

COUNTER

1.14

Counters

1.00

counters

0.96

Activations Density 0.129%

terms related to counterfactual reasoning and its applications

"counter"

words starting with counter

No Comments

No Known Activations