INDEX

Explanations

the word "les" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IsContent

-0.80

 bezeichneter

-0.70

 occaf

-0.66

BufferException

-0.65

 ſche

-0.64

 itſelf

-0.62

GeneratedValue

-0.62

 Sacrific

-0.60

 raiſ

-0.58

 Theſe

-0.56

POSITIVE LOGITS

 CreateTagHelper

0.74

IUrlHelper

0.68

 slow

0.65

La

0.61

jsonwebtoken

0.60

 Resolved

0.59

geted

0.58

 himo

0.57

slow

0.57

 calientes

0.54

Activations Density 0.129%

the word "les" in various contexts

No Comments

No Known Activations