INDEX

Explanations

phrases expressing strong emotions or decisive actions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks indicating exclamations, questions, and statements

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

ancies

-0.77

sels

-0.71

imes

-0.70

ibles

-0.66

oug

-0.66

 warr

-0.64

SPA

-0.64

 accumulated

-0.64

 negatives

-0.63

inous

-0.62

POSITIVE LOGITS

 Saying

0.86

[/

0.83

 Then

0.82

/"

0.82

 Similarly

0.81

 Sometimes

0.79

 Likewise

0.77

 Knowing

0.77

 Nobody

0.76

 Conversely

0.76

Activations Density 0.127%

phrases expressing strong emotions or decisive actions

punctuation marks indicating exclamations, questions, and statements

No Comments

No Known Activations