INDEX

Explanations

terms related to allegations and perceptions of wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 onCreateView

-0.63

-0.56

ómicas

-0.50

ClientSize

-0.49

binary

-0.46

 doublet

-0.45

```

-0.44

 anla

-0.44

POSITIVE LOGITS

 allegedly

0.87

parsedMessage

0.80

EDEFAULT

0.79

 alleged

0.79

 supposedly

0.78

 supuestamente

0.75

 ―――――

0.74

 purported

0.74

 perceived

0.72

LLocation

0.70

Activations Density 0.852%

terms related to allegations and perceptions of wrongdoing

No Comments

No Known Activations