INDEX

Explanations

names of a person, specifically "Linda"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Linda" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

dep

-0.78

flies

-0.78

ngth

-0.74

sed

-0.74

hower

-0.74

ioch

-0.74

tumblr

-0.71

stroke

-0.70

ittance

-0.65

arrass

-0.65

POSITIVE LOGITS

 McMahon

0.84

Sue

0.81

 Linda

0.80

 McCartney

0.80

 Thompson

0.78

ergic

0.77

 Loren

0.75

gdala

0.75

 Cohn

0.75

 Mandela

0.73

Activations Density 0.006%

names of a person, specifically "Linda"

occurrences of the name "Linda" in various contexts

No Comments

No Known Activations