INDEX

Explanations

the phrase "not one" followed by numerical values

oai_token-act-pair · gpt-3.5-turbo

the phrase "not one" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

awar

-0.83

arios

-0.79

 Ezek

-0.72

asar

-0.72

urations

-0.71

awaru

-0.64

arat

-0.62

uberty

-0.60

uart

-0.59

Clar

-0.58

POSITIVE LOGITS

 dime

0.92

 anymore

0.88

ody

0.85

 slightest

0.81

 penny

0.80

nor

0.80

THING

0.77

 else

0.74

 anything

0.73

theless

0.72

Activations Density 0.042%

the phrase "not one" followed by numerical values

the phrase "not one" and its variations

No Comments

No Known Activations