INDEX

Explanations

specific keywords related to coding and setting up software development environments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" or phrases related to locations and contexts

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

 incumb

-0.73

umers

-0.67

HAEL

-0.66

ided

-0.66

scar

-0.65

irl

-0.65

0000000000000000

-0.65

philis

-0.64

inoa

-0.64

ļ

-0.63

POSITIVE LOGITS

 lieu

1.38

 conjunction

1.26

 accordance

1.19

animate

1.08

 unison

1.08

vert

1.07

 addition

1.05

 order

1.03

versely

1.01

bound

1.00

Activations Density 0.261%

specific keywords related to coding and setting up software development environments

occurrences of the word "in" or phrases related to locations and contexts

No Comments

No Known Activations