INDEX

Explanations

concepts related to trust and confidence in relationships and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ITIS

-0.58

enderror

-0.58

ANNES

-0.48

 dandy

-0.47

حياته

-0.47

ensation

-0.47

 Escribe

-0.47

INCLUDED

-0.46

 broom

-0.46

 obstruction

-0.46

POSITIVE LOGITS

 trust

2.56

trust

2.23

Trust

2.13

 trusting

2.08

 Trust

2.04

 TRUST

2.01

 trusts

2.00

 confiance

1.95

 confidence

1.90

 trusted

1.86

Activations Density 0.443%

concepts related to trust and confidence in relationships and interactions

No Comments

No Known Activations