INDEX

Explanations

phrases indicating positive information or developments

oai_token-act-pair · gpt-3.5-turbo

mentions of "good news."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

senal

-0.81

urat

-0.76

sf

-0.70

ONSORED

-0.69

ngth

-0.69

aval

-0.68

 teasp

-0.67

ĸļ

-0.67

 occup

-0.66

 sediment

-0.65

POSITIVE LOGITS

worthiness

0.83

worthy

0.76

peak

0.74

fulness

0.72

 Roundup

0.71

Catholic

0.71

 Subscribe

0.70

feed

0.70

mith

0.69

 Tonight

0.69

Activations Density 0.031%

phrases indicating positive information or developments

mentions of "good news."

No Comments

No Known Activations