INDEX

Explanations

phrases or sentences that introduce further explanation or clarification

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce restatements or explanations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

onel

-0.71

ousel

-0.71

-0.67

adium

-0.62

Sund

-0.61

 Clintons

-0.58

PDATE

-0.58

 Colombia

-0.58

 Columb

-0.57

 Beaver

-0.56

POSITIVE LOGITS

forth

0.93

mith

0.83

tainment

0.80

phony

0.76

terday

0.71

hots

0.68

chwitz

0.68

casters

0.68

 âĶľâĶĢâĶĢ

0.67

clair

0.67

Activations Density 0.029%

phrases or sentences that introduce further explanation or clarification

phrases that introduce restatements or explanations

No Comments

No Known Activations