INDEX

Explanations

occurrences of the word "and."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 itſelf

-0.87

 houſe

-0.85

ſelf

-0.84

 pleaſure

-0.81

 poffible

-0.79

 myſelf

-0.79

 themſelves

-0.77

 Majefty

-0.77

ſelves

-0.73

 fevere

-0.72

POSITIVE LOGITS

it

0.97

 they

0.96

0.95

we

0.90

 there

0.82

you

0.82

MemoryWarning

0.76

he

0.74

AddTagHelper

0.68

 EconPapers

0.66

Activations Density 0.316%

occurrences of the word "and."

No Comments

No Known Activations