INDEX

Explanations

instances of impersonation or imitation

oai_token-act-pair · gpt-3.5-turbo

terms related to impersonation and its various forms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 guiActiveUnfocused

-0.73

FFER

-0.71

-0.70

 RELEASE

-0.70

DERR

-0.70

Bio

-0.70

 Belt

-0.69

Includes

-0.69

 Thrust

-0.68

Streamer

-0.66

POSITIVE LOGITS

 imperson

1.42

 spoof

1.00

ating

0.89

ational

0.86

ators

0.84

azon

0.83

ality

0.83

atural

0.82

acy

0.82

ertodd

0.82

Activations Density 0.010%

instances of impersonation or imitation

terms related to impersonation and its various forms

No Comments

No Known Activations