INDEX

Explanations

words related to negative emotions or situations

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "fl" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

terday

-0.87

RAL

-0.87

TAIN

-0.72

selves

-0.72

HCR

-0.71

OLOGY

-0.70

 Territory

-0.70

eers

-0.66

strate

-0.63

ãĥį

-0.63

POSITIVE LOGITS

ickr

1.21

irting

1.10

imsy

1.09

atter

1.07

uffy

1.04

uff

1.04

utter

1.04

ushing

1.03

oyd

1.03

ashing

1.03

Activations Density 0.013%

words related to negative emotions or situations

instances of the prefix "fl" in various contexts

No Comments

No Known Activations