INDEX

Explanations

numerical values within sentences that may indicate rankings or evaluations

oai_token-act-pair · gpt-3.5-turbo

punctuation, particularly periods and their frequency in various contexts

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

 glim

-0.75

 mosqu

-0.75

imore

-0.71

imar

-0.68

irez

-0.66

ombo

-0.66

itaire

-0.66

 involuntary

-0.65

igning

-0.64

onda

-0.64

POSITIVE LOGITS

icio

0.99

 Parables

0.86

req

0.83

wikipedia

0.82

ItemTracker

0.76

 Retrieved

0.74

assetsadobe

0.73

Ct

0.73

Atk

0.71

 Accessed

0.70

Activations Density 0.131%

numerical values within sentences that may indicate rankings or evaluations

punctuation, particularly periods and their frequency in various contexts

No Comments

No Known Activations