INDEX

Explanations

referential phrases and statements, particularly those that involve reporting or quoting others' words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 CreateTagHelper

-0.89

stagland

-0.69

tonsoft

-0.66

 sandero

-0.64

 AspNetCore

-0.64

 RIAA

-0.63

ofire

-0.63

MENAFN

-0.62

σθαι

-0.62

 Rollo

-0.61

POSITIVE LOGITS

CPtr

0.58

Sol

0.52

 ogen

0.51

0.50

inda

0.48

0.47

Sol

0.47

(__

0.46

Du

0.45

Gar

0.45

Activations Density 4.789%

referential phrases and statements, particularly those that involve reporting or quoting others' words

No Comments

No Known Activations