INDEX

Explanations

Twitter handles

oai_token-act-pair · gpt-3.5-turbo

mentions of Twitter handles or social media usernames

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

 Takeru

-0.82

 vessels

-0.69

 outnumbered

-0.69

 aspir

-0.66

 unsus

-0.65

 exorc

-0.65

 crossover

-0.65

 favors

-0.64

 assum

-0.63

 stricken

-0.63

POSITIVE LOGITS

username

1.01

#$

0.93

Coach

0.91

realDonaldTrump

0.90

deck

0.88

(@

0.85

Tweet

0.82

Official

0.82

nick

0.80

photos

0.79

Activations Density 0.013%

Twitter handles

mentions of Twitter handles or social media usernames

No Comments

No Known Activations