INDEX

Explanations

references to something being done individually, specifically using the term "solo"

oai_token-act-pair · gpt-3.5-turbo

references to solo performances or activities

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

mosp

-0.78

 Hussein

-0.70

 Hussain

-0.66

 inacc

-0.66

 Authorities

-0.65

mos

-0.64

CPC

-0.63

 Ezekiel

-0.62

oras

-0.60

ENCY

-0.60

POSITIVE LOGITS

iliary

0.86

 solo

0.78

spective

0.78

 piano

0.76

ized

0.74

allo

0.73

itus

0.73

andowski

0.72

queue

0.72

ited

0.69

Activations Density 0.016%

references to something being done individually, specifically using the term "solo"

references to solo performances or activities

No Comments

No Known Activations