INDEX

Explanations

references to positions and locations in a narrative

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

objects or items typically associated with or placed on surfaces like tables, chairs, or shelves.

oai_token-act-pair · gpt-4o

Triggered by @christianthto

Prepositions following "the"

np_acts-logits-general · gemini-2.0-flash

places and surfaces

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 تانيه

-0.56

"]();

-0.51

VolleyError

-0.50

 Superhost

-0.49

Attached

-0.49

Listed

-0.48

 ogen

-0.47

 solare

-0.45

 Attached

-0.45

UserScript

-0.45

POSITIVE LOGITS

 ledge

0.79

 table

0.78

 counter

0.75

 edge

0.69

 countertop

0.68

 bench

0.68

 balcony

0.66

 Counter

0.66

 shelf

0.64

 desk

0.63

Activations Density 0.174%

references to positions and locations in a narrative

objects or items typically associated with or placed on surfaces like tables, chairs, or shelves.

Prepositions following "the"

places and surfaces

No Known Activations

references to positions and locations in a narrative

objects or items typically associated with or placed on surfaces like tables, chairs, or shelves.

Prepositions following "the"

places and surfaces

No Known Activations