INDEX

Explanations

phrases related to identifying or investigating causes

oai_token-act-pair · gpt-3.5-turbo

terms associated with identifying causes or factors related to issues or events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aeper

-0.74

ucket

-0.67

PDATE

-0.66

nesday

-0.65

elight

-0.62

olitan

-0.62

uni

-0.62

aredevil

-0.62

sylv

-0.61

 Schwar

-0.61

POSITIVE LOGITS

 cele

1.02

way

0.79

 thereof

0.77

ality

0.77

cause

0.75

 blindness

0.73

WHY

0.70

 attribut

0.69

why

0.68

why

0.68

Activations Density 0.046%

phrases related to identifying or investigating causes

terms associated with identifying causes or factors related to issues or events

No Comments

No Known Activations