INDEX

Explanations

numerical patterns or codes within a text

oai_token-act-pair · gpt-3.5-turbo

numeric values associated with certain entities or data points

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

ingham

-0.86

iday

-0.81

ishing

-0.81

ary

-0.78

iped

-0.76

igating

-0.75

igators

-0.74

ential

-0.74

icut

-0.74

ition

-0.73

POSITIVE LOGITS

teenth

0.94

0.83

0.80

ãģĨ

0.75

cffff

0.74

plate

0.73

ptive

0.72

velop

0.71

LECT

0.71

 Lumpur

0.70

Activations Density 0.083%

numerical patterns or codes within a text

numeric values associated with certain entities or data points

No Comments

No Known Activations