INDEX

Explanations

adjectives related to negative or severe conditions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "severe" and related severity descriptors 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atu

-0.87

wagen

-0.81

ynthesis

-0.81

 Tycoon

-0.77

xxxxxxxx

-0.76

etts

-0.76

cellent

-0.76

raltar

-0.74

ilater

-0.73

kil

-0.72

POSITIVE LOGITS

 depressive

0.87

 enough

0.87

 repercussions

0.87

 earthqu

0.87

 understatement

0.86

 punishments

0.86

 consequences

0.84

 severity

0.84

 traumatic

0.83

 punishment

0.82

Activations Density 0.035%

adjectives related to negative or severe conditions

instances of the word "severe" and related severity descriptors in various contexts

No Comments

No Known Activations