INDEX

Explanations

phrases related to physical locations or destinations

oai_token-act-pair · gpt-3.5-turbo

the word "there" in various contexts

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

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

catentry

-0.76

FTP

-0.65

 Strait

-0.61

get

-0.61

 Paste

-0.61

CJ

-0.61

 Abrams

-0.58

Force

-0.57

 Tank

-0.57

 Chimera

-0.56

POSITIVE LOGITS

abouts

1.34

ilitary

0.86

upon

0.85

OOL

0.79

aturdays

0.77

hedon

0.74

with

0.73

nown

0.71

 guiActiveUn

0.70

ull

0.69

Activations Density 0.077%

phrases related to physical locations or destinations

the word "there" in various contexts

No Comments

No Known Activations