INDEX

Explanations

dates and times written in numerical format

oai_token-act-pair · gpt-3.5-turbo

numerical updates or timestamps related to events

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

 Dragonbound

-0.70

 rook

-0.67

 usher

-0.67

ko

-0.67

 grop

-0.66

 gorilla

-0.66

gy

-0.65

 Origin

-0.64

 chop

-0.63

 stalking

-0.63

POSITIVE LOGITS

1.17

1.14

1.13

1.12

1.11

1.10

1.09

Activations Density 0.022%

dates and times written in numerical format

numerical updates or timestamps related to events

No Comments

No Known Activations