INDEX

Explanations

expressions of existence and being 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 @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 betweenstory

-0.77

AutoScaleMode

-0.65

 Simult

-0.65

AddTagHelper

-0.62

tonode

-0.61

 يتيمه

-0.61

extAlignment

-0.60

melding

-0.60

ցված

-0.58

gonic

-0.58

POSITIVE LOGITS

 very

0.71

 really

0.68

 equivalent

0.68

 indeed

0.62

too

0.58

 also

0.58

 enough

0.57

 already

0.55

 better

0.54

 similar

0.54

Activations Density 0.117%

expressions of existence and being in various contexts

No Comments

No Known Activations