INDEX

Explanations

phrases related to suspicion or accusation

oai_token-act-pair · gpt-3.5-turbo

phrases related to suspicion or accusation

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

retty

-0.71

rio

-0.70

 Palest

-0.69

orkshire

-0.69

rious

-0.66

gomery

-0.65

 arrang

-0.64

resso

-0.64

ahead

-0.64

ussion

-0.63

POSITIVE LOGITS

 Â¯

0.67

âĺħâĺħ

0.61

 fame

0.61

Tre

0.59

mob

0.58

western

0.58

 Django

0.57

 Purpose

0.56

yg

0.55

 Charge

0.55

Activations Density 0.299%

phrases related to suspicion or accusation

phrases related to suspicion or accusation

No Comments

No Known Activations