INDEX

Explanations

phrases related to military or diplomatic assignments

oai_token-act-pair · gpt-3.5-turbo

instances of a specific symbol or character

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

enta

-0.76

 Awakens

-0.68

åŃĲ

-0.62

Gw

-0.60

<@

-0.60

omorphic

-0.59

otta

-0.59

 artif

-0.59

omorph

-0.59

çĭ

-0.58

POSITIVE LOGITS

drivers

0.79

requires

0.76

inducing

0.74

while

0.72

feat

0.72

redients

0.69

devices

0.68

were

0.68

DERR

0.67

eatures

0.66

Activations Density 0.110%

phrases related to military or diplomatic assignments

instances of a specific symbol or character

No Comments

No Known Activations