INDEX

Explanations

events and descriptions related to historical or fictional narratives

oai_token-act-pair · gpt-3.5-turbo

discussions about various events and their interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

geon

-0.85

artisan

-0.74

ench

-0.71

arton

-0.69

 Parables

-0.66

iciency

-0.65

 Mines

-0.65

oug

-0.65

olded

-0.65

wall

-0.64

POSITIVE LOGITS

 transpired

1.22

 unfold

1.14

 unfolded

1.10

uate

1.08

 unfolding

1.05

uating

0.99

 events

0.97

 occurring

0.97

uated

0.93

 occurred

0.88

Activations Density 0.033%

events and descriptions related to historical or fictional narratives

discussions about various events and their interpretations

No Comments

No Known Activations