INDEX

Explanations

words or phrases related to medical conditions or academic titles

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to deception or misleading actions

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

izational

-0.71

 Kenobi

-0.69

unci

-0.69

STER

-0.68

isations

-0.68

rarily

-0.68

eness

-0.68

unciation

-0.67

ested

-0.66

icip

-0.66

POSITIVE LOGITS

utical

0.97

ce

0.89

les

0.87

pter

0.85

0.82

rette

0.81

lled

0.80

re

0.79

llan

0.77

ased

0.76

Activations Density 0.036%

words or phrases related to medical conditions or academic titles

words and phrases related to deception or misleading actions

No Comments

No Known Activations