INDEX

Explanations

references to climbing activities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

addComponent

-0.65

>{@

-0.60

 Slip

-0.59

сут

-0.59

ﬅ

-0.57

 slip

-0.57

Slip

-0.57

mur

-0.56

slip

-0.56

Dam

-0.56

POSITIVE LOGITS

 Climb

1.10

 climb

1.09

Climb

1.08

 climbing

1.04

 myſelf

1.04

 Climbing

1.04

RenderAtEndOf

1.03

climb

1.03

 climbs

1.00

climbing

1.00

Activations Density 0.074%

references to climbing activities or actions

No Comments

No Known Activations