INDEX

Explanations

terminology related to trust and confidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Рабо

-0.82

 Anaconda

-0.81

internalType

-0.79

 barbarous

-0.77

Appender

-0.76

φέρ

-0.76

 Warszawie

-0.75

Representatives

-0.75

 Derivatives

-0.74

 Gillespie

-0.74

POSITIVE LOGITS

 trust

2.21

Trust

2.13

 Trust

2.11

TRUST

2.05

 TRUST

2.04

trust

2.03

 trusts

1.94

 trusting

1.69

 trusted

1.64

 Trusts

1.63

Activations Density 0.051%

terminology related to trust and confidence

No Comments

No Known Activations