INDEX

Explanations

words that connect two ideas together

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" and other connecting phrases that suggest relatedness or continuation in ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Buk

-0.73

 Span

-0.72

 Yuan

-0.71

 Signal

-0.69

 Brewer

-0.69

 Entered

-0.69

 Knot

-0.69

 Sparks

-0.69

 Applicant

-0.68

 Tile

-0.68

POSITIVE LOGITS

theless

1.35

selves

1.29

terday

1.20

redients

1.18

fore

1.18

etheless

1.08

mosp

1.07

vernment

1.05

have

1.05

wards

1.01

Activations Density 0.165%

words that connect two ideas together

the conjunction "and" and other connecting phrases that suggest relatedness or continuation in ideas

No Comments

No Known Activations