INDEX

Explanations

mentions of lakes in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to lakes

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

 Goodwin

-0.77

auld

-0.76

cul

-0.74

aldi

-0.68

ENTS

-0.68

Ô

-0.68

nant

-0.68

LM

-0.68

llah

-0.66

Fu

-0.65

POSITIVE LOGITS

 lake

0.98

 lakes

0.93

tub

0.92

front

0.82

 Erie

0.82

 ponds

0.81

 basin

0.81

ishly

0.80

omed

0.79

urst

0.77

Activations Density 0.020%

mentions of lakes in various contexts

references to lakes

No Comments

No Known Activations