INDEX

Explanations

words related to actions of obstructing or preventing something

oai_token-act-pair · gpt-3.5-turbo

instances of the words "blocking" and "blocked"

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

llers

-0.80

gow

-0.80

ller

-0.74

lli

-0.73

brates

-0.70

BUS

-0.70

prise

-0.68

mble

-0.68

brate

-0.68

EMBER

-0.65

POSITIVE LOGITS

busters

0.97

quote

0.93

buster

0.88

aded

0.84

 blocking

0.83

ades

0.83

picking

0.76

ading

0.76

chains

0.73

osuke

0.72

Activations Density 0.026%

words related to actions of obstructing or preventing something

instances of the words "blocking" and "blocked"

No Comments

No Known Activations