INDEX

Explanations

discussions of personal experiences, often with emotional or controversial implications

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

 deres

-0.90

 ourselves

-0.80

彼らは

-0.79

 yourselves

-0.74

 deras

-0.71

 eorum

-0.67

 loro

-0.65

 kanilang

-0.65

 unison

-0.60

seamnă

-0.60

POSITIVE LOGITS

 himself

1.86

his

1.82

himself

1.49

his

1.31

 seinem

1.16

 seiner

1.12

 kanyang

1.04

 seines

1.03

 dirinya

1.00

 Himself

0.98

Activations Density 1.236%

discussions of personal experiences, often with emotional or controversial implications

No Comments

No Known Activations