INDEX

Explanations

phrases or names related to a specific person named "Sashi"

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities associated with the name "Takahashi."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

sworth

-0.89

rified

-0.79

ship

-0.71

eering

-0.69

ilater

-0.68

course

-0.67

names

-0.66

paper

-0.66

 Lazarus

-0.66

space

-0.65

POSITIVE LOGITS

ya

1.03

Äĩ

0.88

pora

0.88

emi

0.83

á¹

0.81

ashi

0.81

ibi

0.80

imi

0.79

unta

0.79

iku

0.78

Activations Density 0.020%

phrases or names related to a specific person named "Sashi"

references to specific individuals or entities associated with the name "Takahashi."

No Comments

No Known Activations