INDEX

Explanations

terms related to negative events or actions with significant impact

oai_token-act-pair · gpt-3.5-turbo

instances of the word "blow" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ript

-0.89

 Malays

-0.68

 Beir

-0.65

iosity

-0.65

nesota

-0.65

kson

-0.64

ively

-0.63

 Qian

-0.62

 Norn

-0.61

herty

-0.60

POSITIVE LOGITS

hard

1.17

gun

1.08

guns

1.03

job

1.01

blow

0.96

pipe

0.94

jobs

0.94

out

0.93

hole

0.92

outs

0.91

Activations Density 0.022%

terms related to negative events or actions with significant impact

instances of the word "blow" in various contexts

No Comments

No Known Activations