INDEX

Explanations

the word "Banks" along with various contexts and associated information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Banks."

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

 Rodham

-0.76

âĶĢâĶĢâĶĢâĶĢ

-0.69

itably

-0.69

nder

-0.65

ifa

-0.63

hibition

-0.63

ACTED

-0.62

phant

-0.61

 Scotia

-0.61

ormon

-0.60

POSITIVE LOGITS

hops

1.05

hirt

1.04

haw

0.96

ettings

0.91

alez

0.89

cape

0.89

hop

0.88

yip

0.88

yk

0.85

ingham

0.84

Activations Density 0.056%

the word "Banks" along with various contexts and associated information

occurrences of the name "Banks."

No Comments

No Known Activations