INDEX

Explanations

the name "Gabriel" which may indicate a strong association with this specific name

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Gabriel"

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

req

-0.92

ramid

-0.80

ulhu

-0.79

meal

-0.79

ocard

-0.78

perature

-0.77

under

-0.74

llular

-0.74

ĵĺ

-0.73

romancer

-0.72

POSITIVE LOGITS

 Gabriel

0.93

le

0.92

ual

0.89

mas

0.82

 Garc

0.80

 Byrne

0.79

sson

0.78

 Uriel

0.78

IAN

0.73

 Raphael

0.73

Activations Density 0.017%

the name "Gabriel" which may indicate a strong association with this specific name

mentions of the name "Gabriel"

No Comments

No Known Activations