INDEX

Explanations

references to horns, particularly those related to rhinoceros horns

oai_token-act-pair · gpt-3.5-turbo

references to horns, particularly in relation to rhinoceroses

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

ricular

-0.79

anmar

-0.76

ultz

-0.73

tun

-0.72

ĵĺ

-0.71

essen

-0.71

tube

-0.70

locks

-0.70

ombat

-0.70

safe

-0.70

POSITIVE LOGITS

 horns

0.79

frog

0.75

 horn

0.71

aurus

0.70

ophone

0.67

ensed

0.67

 Messi

0.63

OGR

0.63

cir

0.61

 deaf

0.61

Activations Density 0.063%

references to horns, particularly those related to rhinoceros horns

references to horns, particularly in relation to rhinoceroses

No Comments

No Known Activations