INDEX

Explanations

references to different levels in a hierarchical system

oai_token-act-pair · gpt-3.5-turbo

references to levels in a gaming context

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

vous

-0.84

oute

-0.81

rontal

-0.76

å¥³

-0.73

uter

-0.67

ILLE

-0.67

 Sidd

-0.66

 Leilan

-0.66

vot

-0.66

ãĥĨãĤ£

-0.64

POSITIVE LOGITS

level

0.78

 attainment

0.71

 advancement

0.66

ottage

0.65

 crossings

0.64

 attained

0.64

 certific

0.63

casting

0.63

ership

0.63

Level

0.62

Activations Density 0.026%

references to different levels in a hierarchical system

references to levels in a gaming context

No Comments

No Known Activations