INDEX

Explanations

references to statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stated" 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 @ 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

xtap

-0.77

 Carbuncle

-0.74

 Dome

-0.71

 Torn

-0.67

avascript

-0.66

estern

-0.64

awaru

-0.62

brance

-0.62

Haz

-0.61

iling

-0.60

POSITIVE LOGITS

gow

0.89

 unequivocally

0.88

 bluntly

0.79

ance

0.74

 emphatically

0.71

REAM

0.71

 plainly

0.71

irection

0.69

TextColor

0.67

idate

0.65

Activations Density 0.030%

references to statements made by individuals

instances of the word "stated" in various contexts

No Comments

No Known Activations