INDEX

Explanations

numerical values related to specific identifiers, possibly referencing technical data or locations within a longer document

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

prises

-0.77

olicy

-0.76

arte

-0.71

liga

-0.71

hran

-0.70

oken

-0.69

nesday

-0.69

ItemTracker

-0.68

ĸļ

-0.68

alties

-0.66

POSITIVE LOGITS

0.99

th

0.84

ZI

0.74

0.72

0.70

 deficient

0.68

0.67

Activations Density 0.021%

numerical values related to specific identifiers, possibly referencing technical data or locations within a longer document

numerical data or statistics

No Comments

No Known Activations