INDEX

Explanations

phrases related to specific names or places, specifically those starting with "Har"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Har."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

éĹĺ

-0.93

eers

-0.75

 Tone

-0.71

ĸļ

-0.69

URES

-0.68

UCT

-0.66

 Emir

-0.65

REDACTED

-0.64

anwhile

-0.64

xual

-0.63

POSITIVE LOGITS

rier

1.12

assment

1.11

rod

1.09

riers

1.08

vard

1.04

rim

1.02

rah

1.02

rowing

0.96

ried

0.96

assed

0.91

Activations Density 0.025%

phrases related to specific names or places, specifically those starting with "Har"

references to the name "Har."

No Comments

No Known Activations