INDEX

Explanations

references to rivers

oai_token-act-pair · gpt-3.5-turbo

mentions of rivers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Reloaded

-0.71

 Mutant

-0.70

 Horowitz

-0.69

Mach

-0.66

practice

-0.63

Toy

-0.61

 Upton

-0.61

Fn

-0.59

 Latest

-0.59

ACH

-0.58

POSITIVE LOGITS

front

1.02

bank

0.97

 basin

0.96

banks

0.90

 valley

0.89

 rivers

0.88

 river

0.87

 valleys

0.87

ine

0.86

course

0.84

Activations Density 0.031%

references to rivers

mentions of rivers

No Comments

No Known Activations