INDEX

Explanations

the word "if" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

conditional statements or hypothetical scenarios

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

 depths

-0.69

omi

-0.65

GMT

-0.64

WAYS

-0.64

================================================================

-0.63

holm

-0.62

nect

-0.61

avor

-0.61

grey

-0.60

ho

-0.59

POSITIVE LOGITS

yip

0.93

fy

0.82

 Gutenberg

0.76

 thou

0.75

you

0.74

ever

0.69

 Melania

0.68

rame

0.67

yon

0.67

soever

0.67

Activations Density 0.033%

the word "if" followed by a numerical value

conditional statements or hypothetical scenarios

No Comments

No Known Activations