INDEX

Explanations

references to guests and participants 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

writeFieldEnd

-0.76

istoitu

-0.75

 للمعارف

-0.75

pexpr

-0.62

principalTable

-0.62

 Emits

-0.61

 retailer

-0.60

KELEY

-0.57

olites

-0.57

PTEMBER

-0.56

POSITIVE LOGITS

Guest

1.13

 Guest

1.13

 guest

1.10

 audience

1.10

 attendee

1.05

 guests

1.04

 spectators

1.02

 attendees

1.01

guest

1.01

 viewers

0.94

Activations Density 3.135%

references to guests and participants in various contexts

No Comments

No Known Activations