INDEX

Explanations

phrases related to possession or lack thereof

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "have"

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

ilation

-0.72

nown

-0.64

catentry

-0.61

stre

-0.61

externalActionCode

-0.58

 guiName

-0.58

sequent

-0.58

 neigh

-0.56

later

-0.56

soType

-0.55

POSITIVE LOGITS

 been

0.84

 recourse

0.82

 enough

0.79

 permission

0.78

 access

0.77

gotten

0.73

 sufficient

0.71

 anymore

0.71

 necessarily

0.70

any

0.70

Activations Density 0.081%

phrases related to possession or lack thereof

occurrences of the word "have"

No Comments

No Known Activations