INDEX

Explanations

phrases related to news or events

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ealous

-0.89

sequently

-0.81

FW

-0.81

qus

-0.77

ity

-0.76

swick

-0.75

imei

-0.72

eed

-0.72

Secondly

-0.71

tics

-0.71

POSITIVE LOGITS

 comedian

0.84

 Donald

0.82

 filmmaker

0.81

 Rodrigo

0.79

 rapper

0.78

 astronomers

0.76

 photographer

0.74

 Mehran

0.73

 Barack

0.73

 embattled

0.73

Activations Density 0.286%

phrases related to news or events

punctuation marks, particularly commas

No Comments

No Known Activations