INDEX

Explanations

references to literal or metaphorical "waves."

oai_token-act-pair · gpt-3.5-turbo

references to "waves" in various contexts

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

orate

-0.80

heid

-0.78

rontal

-0.76

ioch

-0.72

ancies

-0.72

azeera

-0.71

mingham

-0.71

uments

-0.69

ivia

-0.69

atem

-0.67

POSITIVE LOGITS

guide

1.02

form

0.94

forms

0.86

front

0.86

wave

0.85

 wave

0.85

rers

0.83

stakes

0.81

boat

0.81

tro

0.77

Activations Density 0.020%

references to literal or metaphorical "waves."

references to "waves" in various contexts

No Comments

No Known Activations