INDEX

Explanations

mentions of something or someone being a standout or exemplary representation

oai_token-act-pair · gpt-3.5-turbo

references to "poster" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

REE

-0.69

Ago

-0.69

displayText

-0.67

ESSION

-0.67

%]

-0.65

ostics

-0.65

hews

-0.64

IVE

-0.63

redo

-0.61

IVES

-0.61

POSITIVE LOGITS

iors

0.97

ity

0.90

ior

0.89

boy

0.87

 poster

0.86

boys

0.83

pillar

0.79

clip

0.79

onymous

0.78

boards

0.76

Activations Density 0.041%

mentions of something or someone being a standout or exemplary representation

references to "poster" in various contexts

No Comments

No Known Activations