INDEX

Explanations

phrases indicating involvement or participation in various activities or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ratulations

-0.82

iren

-0.68

ians

-0.67

uses

-0.66

username

-0.64

glass

-0.63

iance

-0.62

LOG

-0.62

named

-0.61

AppData

-0.61

POSITIVE LOGITS

ordinate

1.05

 constructing

0.94

 organising

0.93

 shaping

0.93

 crafting

0.92

 facilitating

0.90

 transporting

0.88

 overseeing

0.88

 designing

0.88

 negotiations

0.87

Activations Density 0.103%

phrases indicating involvement or participation in various activities or events

occurrences of the word "in."

No Comments

No Known Activations