INDEX

Explanations

mentions of performing activities alone or individually

oai_token-act-pair · gpt-3.5-turbo

references to solo acts or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mosp

-0.77

 Hussain

-0.68

cale

-0.68

 Authorities

-0.67

oras

-0.67

ENE

-0.66

 inacc

-0.66

mos

-0.64

older

-0.64

 Pearce

-0.63

POSITIVE LOGITS

iliary

0.90

 piano

0.80

 acoustic

0.78

 solo

0.77

icated

0.76

spective

0.74

 outing

0.71

ilus

0.71

ized

0.70

 ascent

0.70

Activations Density 0.020%

mentions of performing activities alone or individually

references to solo acts or activities

No Comments

No Known Activations