INDEX

Explanations

verbs related to imposing restrictions or limits

oai_token-act-pair · gpt-3.5-turbo

terms related to limitations or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IRED

-0.74

Champ

-0.72

OF

-0.69

Sham

-0.69

united

-0.68

FORE

-0.66

ãĤĬ

-0.66

GROUND

-0.66

ublic

-0.65

ands

-0.65

POSITIVE LOGITS

 access

0.94

 visitation

0.83

 mobility

0.83

 unnecessary

0.77

 consumption

0.77

 unrestricted

0.76

 runaway

0.76

ively

0.75

 visibility

0.75

 withdrawals

0.74

Activations Density 0.059%

verbs related to imposing restrictions or limits

terms related to limitations or restrictions

No Comments

No Known Activations