INDEX

Explanations

phrases related to problem-solving or decision-making

oai_token-act-pair · gpt-3.5-turbo

references to problem-solving or figuring things out

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

ibaba

-0.70

nor

-0.70

ription

-0.65

rait

-0.63

VIDEO

-0.63

interrupted

-0.61

court

-0.60

 accompanied

-0.59

ewitness

-0.59

vation

-0.58

POSITIVE LOGITS

out

0.97

 prominently

0.81

 skating

0.78

OUT

0.74

heads

0.72

istically

0.70

out

0.69

acci

0.65

ometry

0.65

avia

0.64

Activations Density 0.025%

phrases related to problem-solving or decision-making

references to problem-solving or figuring things out

No Comments

No Known Activations