INDEX

Explanations

specific scenes or moments in various media forms

oai_token-act-pair · gpt-3.5-turbo

mentions of significant scenes or moments in films or shows

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

properties

-0.73

athered

-0.71

jong

-0.71

opes

-0.70

 contracting

-0.66

addons

-0.66

cale

-0.65

verning

-0.65

ailable

-0.64

haar

-0.63

POSITIVE LOGITS

 involving

0.82

 uttered

0.76

 spree

0.68

 aired

0.66

 sequence

0.65

 outburst

0.63

 featuring

0.61

 volley

0.61

 replay

0.61

 mont

0.60

Activations Density 0.447%

specific scenes or moments in various media forms

mentions of significant scenes or moments in films or shows

No Comments

No Known Activations