INDEX

Explanations

phrases related to specific skills or attributes

oai_token-act-pair · gpt-3.5-turbo

terms related to skill sets and supply chains

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

NL

-0.81

Gaming

-0.68

ritch

-0.62

isl

-0.62

ãģĤ

-0.61

Union

-0.61

paren

-0.60

disc

-0.60

lar

-0.60

pload

-0.59

POSITIVE LOGITS

 continuum

0.75

atically

0.72

 dictates

0.68

 selector

0.68

 optimized

0.66

 optimization

0.65

 sophistication

0.65

atics

0.65

 requirements

0.64

 complying

0.64

Activations Density 0.279%

phrases related to specific skills or attributes

terms related to skill sets and supply chains

No Comments

No Known Activations