INDEX

Explanations

occurrences of the term "human rights" and related phrases in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

]$}

-0.82

parsedMessage

-0.82

期刊论文

-0.81

\{\\

-0.81

Composable

-0.80

findpost

-0.79

RenderAtEndOf

-0.79

moreland

-0.78

 Cleary

-0.78

FieldNumber

-0.77

POSITIVE LOGITS

 rights

2.20

 Rights

2.05

rights

1.88

 RIGHTS

1.82

Rights

1.79

 derechos

1.39

 direitos

1.31

 droits

1.14

 diritti

1.09

 Rechte

1.05

Activations Density 0.057%

occurrences of the term "human rights" and related phrases in various contexts

No Comments

No Known Activations