INDEX

Explanations

phrases related to locations or concepts that are physically above or below something else

oai_token-act-pair · gpt-3.5-turbo

references to authority and societal norms

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

sbm

-0.74

PLA

-0.70

 Cosponsors

-0.69

 alike

-0.68

 ahead

-0.67

PsyNetMessage

-0.67

-0.66

DAQ

-0.66

 followed

-0.64

======

-0.62

POSITIVE LOGITS

 bounds

1.07

 confines

1.02

 boundaries

0.97

 limits

0.96

 horizon

0.93

 borders

0.88

 threshold

0.87

 walls

0.82

 veil

0.82

 limitations

0.75

Activations Density 0.166%

phrases related to locations or concepts that are physically above or below something else

references to authority and societal norms

No Comments

No Known Activations