INDEX

Explanations

words related to geographical locations and organizations

oai_token-act-pair · gpt-3.5-turbo

variations of the prefix "un-" and related roots

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

 Ples

-0.66

 Logged

-0.62

dod

-0.62

 Rams

-0.61

doctor

-0.60

 vendor

-0.59

 Morty

-0.58

BACK

-0.57

sticks

-0.57

 subp

-0.57

POSITIVE LOGITS

ailability

0.91

QL

0.89

oppable

0.89

cedented

0.78

akable

0.76

quished

0.75

ernel

0.72

ables

0.71

Ire

0.68

owship

0.68

Activations Density 0.079%

words related to geographical locations and organizations

variations of the prefix "un-" and related roots

No Comments

No Known Activations