INDEX

Explanations

mentions of the name "Verhagen" with high activation values

oai_token-act-pair · gpt-3.5-turbo

the letter 'h' 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 @ 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

 Clicker

-0.80

enhagen

-0.79

aution

-0.79

fman

-0.74

 nomine

-0.73

ãĥ¯

-0.73

 flush

-0.73

 tremend

-0.71

 mosqu

-0.68

psey

-0.67

POSITIVE LOGITS

orses

1.22

awk

1.17

oused

1.12

ollow

1.12

ulk

1.12

wy

1.07

ometown

1.06

anging

1.06

ythm

1.06

undred

1.05

Activations Density 0.041%

mentions of the name "Verhagen" with high activation values

the letter 'h' in various contexts

No Comments

No Known Activations