INDEX

Explanations

words related to adaptation or adjustment

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lim" related to limitations

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

ICLE

-0.82

chnology

-0.77

 Blessed

-0.70

 Hurricanes

-0.64

HE

-0.63

 Kirin

-0.62

wright

-0.62

Ich

-0.61

DEP

-0.59

 Breaking

-0.57

POSITIVE LOGITS

entary

1.07

psons

0.98

ogy

0.90

bered

0.90

olition

0.90

pse

0.89

inatory

0.87

pson

0.87

inished

0.87

onial

0.86

Activations Density 0.018%

words related to adaptation or adjustment

occurrences of the word "lim" related to limitations

No Comments

No Known Activations