INDEX

Explanations

references to medical or chemical terms related to endocrine disruption and toxicity

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

figures or tables

np_acts-logits-general · gemini-2.0-flash

citations and references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ItemBackground

-0.79

ništvo

-0.66

jsii

-0.62

boutin

-0.58

 tief

-0.57

 algo

-0.56

بية

-0.55

:✨

-0.53

عبة

-0.53

fhir

-0.53

POSITIVE LOGITS

1.08

 Majefty

0.92

 themſelves

0.88

 itſelf

0.86

 myſelf

0.85

 whoſe

0.80

 greateſt

0.79

ſelves

0.77

 Monfieur

0.76

 Jefus

0.74

Activations Density 1.438%

references to medical or chemical terms related to endocrine disruption and toxicity

figures or tables

citations and references

No Comments

No Known Activations