INDEX

Explanations

phrases related to reaffirmation or reiteration

oai_token-act-pair · gpt-3.5-turbo

words related to restating or confirming previous statements

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

pmwiki

-0.76

erenn

-0.73

bestos

-0.71

iop

-0.70

gins

-0.70

oping

-0.69

iox

-0.68

 noses

-0.66

©¶æ

-0.65

enium

-0.65

POSITIVE LOGITS

 reaff

0.90

irmation

0.87

 affirmation

0.83

irmed

0.82

 vows

0.81

 reiter

0.81

irming

0.78

 affirm

0.77

raints

0.76

 declarations

0.75

Activations Density 0.036%

phrases related to reaffirmation or reiteration

words related to restating or confirming previous statements

No Comments

No Known Activations