INDEX

Explanations

occurrences of a specific term or phrase, possibly associated with a particular concept or topic

oai_token-act-pair · gpt-3.5-turbo

references to specific propositions or legislative measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.77

soever

-0.72

 GOODMAN

-0.69

 Carib

-0.67

cules

-0.67

keeper

-0.67

realDonaldTrump

-0.67

ãĤ¼ãĤ¦ãĤ¹

-0.66

 fingertips

-0.66

esome

-0.65

POSITIVE LOGITS

onents

1.34

aganda

1.25

osed

1.23

ulsion

1.22

osition

1.21

ensity

1.16

onent

1.15

ulsive

1.06

hetical

1.01

ractor

0.99

Activations Density 0.007%

occurrences of a specific term or phrase, possibly associated with a particular concept or topic

references to specific propositions or legislative measures

No Comments

No Known Activations