INDEX

Explanations

instances of the word "eventually."

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

phrases related to events occuring at a later point in time

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lua

-0.75

yet

-0.71

atures

-0.69

VK

-0.69

 Crusader

-0.65

teen

-0.64

sheet

-0.63

ocker

-0.62

maid

-0.61

artisan

-0.61

POSITIVE LOGITS

 succumb

0.91

 culmin

0.90

 relent

0.84

 succumbed

0.84

 succeed

0.80

icably

0.79

 settle

0.78

 dwind

0.78

 culminating

0.77

 assimil

0.77

Activations Density 0.027%

instances of the word "eventually."

phrases related to events occuring at a later point in time

No Comments

No Known Activations