INDEX

Explanations

occurrences of specific terms related to technology or software updates

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

onica

-0.72

ities

-0.70

ITY

-0.67

 Reach

-0.66

ITIES

-0.65

asper

-0.65

jamin

-0.63

 Mahjong

-0.62

iod

-0.61

IRO

-0.61

POSITIVE LOGITS

vre

1.02

nda

0.89

lease

0.84

nesota

0.81

ĸļ

0.80

llers

0.80

eport

0.80

herty

0.76

rette

0.75

retty

0.75

Activations Density 0.051%

occurrences of specific terms related to technology or software updates

proper nouns related to specific individuals or entities

No Comments

No Known Activations