INDEX

Explanations

numbers indicating quantity or time intervals

oai_token-act-pair · gpt-3.5-turbo

quantitative measures and expressions of limits or capacities

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

liest

-0.86

Reviewer

-0.84

lance

-0.77

Pear

-0.72

tery

-0.72

ãĥĺ

-0.69

ãĥ£

-0.67

 Corpus

-0.67

Agent

-0.64

Redd

-0.63

POSITIVE LOGITS

ousand

0.72

 depending

0.71

kw

0.71

 detect

0.71

phrine

0.70

 overload

0.70

 maximum

0.68

xual

0.68

 sidx

0.68

abyte

0.68

Activations Density 0.110%

numbers indicating quantity or time intervals

quantitative measures and expressions of limits or capacities

No Comments

No Known Activations