INDEX

Explanations

references to specific legal systems or institutions

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and names associated with excitement or conflict

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

itable

-0.90

yip

-0.78

 cannon

-0.75

 disclaim

-0.73

zik

-0.73

ould

-0.73

ble

-0.70

conservancy

-0.70

ball

-0.69

table

-0.68

POSITIVE LOGITS

ively

0.91

alez

0.82

gow

0.75

OWER

0.73

iveness

0.71

iar

0.67

ority

0.67

 warr

0.66

daq

0.66

 endings

0.66

Activations Density 0.044%

references to specific legal systems or institutions

references to specific locations and names associated with excitement or conflict

No Comments

No Known Activations