INDEX

Explanations

locations where something is found or discovered

oai_token-act-pair · gpt-3.5-turbo

instances of the word "found" related to objects or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tert

-0.74

 horm

-0.70

creation

-0.64

enta

-0.61

inion

-0.61

ankind

-0.61

 Britann

-0.60

Xen

-0.59

VP

-0.59

nom

-0.58

POSITIVE LOGITS

âĸĪ

0.85

Ô

0.84

gdala

0.81

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

0.78

¿½

0.78

EMS

0.72

ymes

0.71

dylib

0.71

andals

0.69

 Guilty

0.68

Activations Density 0.061%

locations where something is found or discovered

instances of the word "found" related to objects or people

No Comments

No Known Activations