INDEX

Explanations

words related to bureaucratic processes or obstacles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "red."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

UGH

-0.83

ernel

-0.81

ILA

-0.79

Reloaded

-0.77

 Lank

-0.77

XT

-0.76

agall

-0.74

Ö¼

-0.73

OTOS

-0.71

=-=-

-0.69

POSITIVE LOGITS

neck

1.15

oubt

1.11

rawn

1.10

efined

1.09

 velvet

1.05

oub

1.02

headed

1.00

iscovered

0.99

iscovery

0.98

iscover

0.97

Activations Density 0.024%

words related to bureaucratic processes or obstacles

occurrences of the word "red."

No Comments

No Known Activations