INDEX

Explanations

words related to locations, particularly featuring the string "ne" followed by a number

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rador

-0.85

rament

-0.83

hips

-0.78

ENCY

-0.75

inarily

-0.74

olicy

-0.71

ELF

-0.70

awaru

-0.69

ernaut

-0.69

enhagen

-0.68

POSITIVE LOGITS

jad

1.05

cht

0.96

cker

0.96

gger

0.96

phrine

0.96

arest

0.94

quin

0.93

cks

0.91

gan

0.90

hill

0.87

Activations Density 0.029%

words related to locations, particularly featuring the string "ne" followed by a number

No Comments

No Known Activations