INDEX

Explanations

places or locations within Manhattan

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Manhattan."

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

rar

-0.79

utic

-0.77

orders

-0.77

ebook

-0.76

cific

-0.75

ional

-0.75

tnc

-0.74

np

-0.74

doors

-0.71

ression

-0.71

POSITIVE LOGITS

 Beach

1.07

 Borough

1.06

 skyline

0.93

 Manhattan

0.91

 borough

0.88

 skysc

0.84

 Island

0.83

 apartment

0.80

 Declaration

0.79

 Harbor

0.79

Activations Density 0.018%

places or locations within Manhattan

occurrences of the word "Manhattan."

No Comments

No Known Activations